Quantize Llama 2 models using ggml

🗣️ Large Language Model Course

❤️ Created by @maximelabonne.

Usage

MODEL_ID: The ID of the model to quantize (e.g., mlabonne/EvolCodeLlama-7b).
QUANTIZATION_METHOD: The quantization method to use.

Quantization methods

The names of the quantization methods follow the naming convention: "q" + the number of bits + the variant used (detailed below). Here is a list of all the possible quant methods and their corresponding use cases, based on model cards made by TheBloke:

q2_k: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
q3_k_l: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
q3_k_m: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
q3_k_s: Uses Q3_K for all tensors
q4_0: Original quant method, 4-bit.
q4_1: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
q4_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
q4_k_s: Uses Q4_K for all tensors
q5_0: Higher accuracy, higher resource usage and slower inference.
q5_1: Even higher accuracy, resource usage and slower inference.
q5_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
q5_k_s: Uses Q5_K for all tensors
q6_k: Uses Q8_K for all tensors
q8_0: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

As a rule of thumb, I recommend using Q5_K_M as it preserves most of the model's performance. Alternatively, you can use Q4_K_M if you want to save some memory. In general, K_M versions are better than K_S versions. I cannot recommend Q2_K or Q3_* versions, as they drastically decrease model performance.

In [ ]:

# Variables
MODEL_ID = "mlabonne/EvolCodeLlama-7b"
QUANTIZATION_METHODS = ["q4_k_m"]

# Constants
MODEL_NAME = MODEL_ID.split('/')[-1]
GGML_VERSION = "gguf"

# Install llama.cpp
!git clone https://github.com/ggerganov/llama.cpp
!cd llama.cpp && git pull && make clean && LLAMA_CUBLAS=1 make
!pip install -r llama.cpp/requirements.txt

# Download model
!git lfs install
!git clone https://huggingface.co/{MODEL_ID}

# Convert to fp16
fp16 = f"{MODEL_NAME}/{MODEL_NAME.lower()}.{GGML_VERSION}.fp16.bin"
!python llama.cpp/convert.py {MODEL_NAME} --outtype f16 --outfile {fp16}

# Quantize the model for each method in the QUANTIZATION_METHODS list
for method in QUANTIZATION_METHODS:
    qtype = f"{MODEL_NAME}/{MODEL_NAME.lower()}.{GGML_VERSION}.{method}.bin"
    !./llama.cpp/quantize {fp16} {qtype} {method}

ggml_init_cublas: found 1 CUDA devices:
  Device 0: Tesla T4, compute capability 7.5
main: build = 1100 (dd0dc36)
main: quantizing 'EvolCodeLlama-7b/evolcodellama-7b.gguf.fp16.bin' to 'EvolCodeLlama-7b/evolcodellama-7b.gguf.q4_k_s.bin' as Q4_K_S
llama_model_loader: loaded meta data with 16 key-value pairs and 291 tensors from EvolCodeLlama-7b/evolcodellama-7b.gguf.fp16.bin (version GGUF V1 (support until nov 2023))
llama_model_loader: - tensor    0:                token_embd.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:              blk.0.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    2:              blk.0.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:         blk.0.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    9:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   10:              blk.1.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   11:              blk.1.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:         blk.1.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   19:              blk.2.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   20:              blk.2.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:         blk.2.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   24:              blk.2.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   28:              blk.3.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   29:              blk.3.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:         blk.3.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   33:              blk.3.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   37:              blk.4.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   38:              blk.4.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:         blk.4.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   42:              blk.4.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   46:              blk.5.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   47:              blk.5.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:         blk.5.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   51:              blk.5.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   55:              blk.6.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   56:              blk.6.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:         blk.6.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   60:              blk.6.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   64:              blk.7.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   65:              blk.7.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:         blk.7.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   69:              blk.7.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   73:              blk.8.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   74:              blk.8.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:         blk.8.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   78:              blk.8.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   82:              blk.9.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   83:              blk.9.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:         blk.9.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   87:              blk.9.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   91:             blk.10.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   92:             blk.10.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:        blk.10.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   96:             blk.10.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  100:             blk.11.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  101:             blk.11.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:        blk.11.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  105:             blk.11.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  109:             blk.12.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  110:             blk.12.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:        blk.12.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  114:             blk.12.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  118:             blk.13.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  119:             blk.13.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:        blk.13.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  123:             blk.13.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  127:             blk.14.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  128:             blk.14.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:        blk.14.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  132:             blk.14.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  136:             blk.15.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  137:             blk.15.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:        blk.15.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  141:             blk.15.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  145:             blk.16.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  146:             blk.16.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:        blk.16.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  150:             blk.16.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  154:             blk.17.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  155:             blk.17.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:        blk.17.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  159:             blk.17.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  163:             blk.18.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  164:             blk.18.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:        blk.18.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  168:             blk.18.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  172:             blk.19.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  173:             blk.19.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:        blk.19.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  177:             blk.19.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  181:             blk.20.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  182:             blk.20.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:        blk.20.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  186:             blk.20.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  190:             blk.21.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  191:             blk.21.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:        blk.21.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  195:             blk.21.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  199:             blk.22.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  200:             blk.22.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:        blk.22.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  204:             blk.22.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  208:             blk.23.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  209:             blk.23.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:        blk.23.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  213:             blk.23.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  217:             blk.24.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  218:             blk.24.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:        blk.24.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  222:             blk.24.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  226:             blk.25.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:             blk.25.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:        blk.25.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  231:             blk.25.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  235:             blk.26.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:             blk.26.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:        blk.26.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  240:             blk.26.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  244:             blk.27.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:             blk.27.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:        blk.27.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  249:             blk.27.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  253:             blk.28.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:             blk.28.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:        blk.28.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  258:             blk.28.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  262:             blk.29.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:             blk.29.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:        blk.29.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  267:             blk.29.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  271:             blk.30.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:             blk.30.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:        blk.30.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  276:             blk.30.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  280:             blk.31.attn_q.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:             blk.31.attn_k.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_v.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:        blk.31.attn_output.weight f16      [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  285:             blk.31.ffn_up.weight f16      [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_down.weight f16      [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  289:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:                    output.weight f16      [  4096, 32016,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str     
llama_model_loader: - kv   1:                               general.name str     
llama_model_loader: - kv   2:                       llama.context_length u32     
llama_model_loader: - kv   3:                     llama.embedding_length u32     
llama_model_loader: - kv   4:                          llama.block_count u32     
llama_model_loader: - kv   5:                  llama.feed_forward_length u32     
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     
llama_model_loader: - kv   7:                 llama.attention.head_count u32     
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     
llama_model_loader: - kv  10:                       llama.rope.freq_base f32     
llama_model_loader: - kv  11:                          general.file_type u32     
llama_model_loader: - kv  12:                       tokenizer.ggml.model str     
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr     
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr     
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr     
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:  226 tensors
llama_model_quantize_internal: meta size = 741408 bytes
[   1/ 291]                    token_embd.weight - [ 4096, 32016,     1,     1], type =    f16, quantizing to q4_K .. size =   250.12 MB ->    70.35 MB | hist: 
[   2/ 291]                  blk.0.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[   3/ 291]                  blk.0.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[   4/ 291]                  blk.0.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    32.00 MB ->    11.00 MB | hist: 
[   5/ 291]             blk.0.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[   6/ 291]                blk.0.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[   7/ 291]                  blk.0.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[   8/ 291]                blk.0.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    86.00 MB ->    29.56 MB | hist: 
[   9/ 291]               blk.0.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  10/ 291]                blk.0.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  11/ 291]                  blk.1.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  12/ 291]                  blk.1.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  13/ 291]                  blk.1.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    32.00 MB ->    11.00 MB | hist: 
[  14/ 291]             blk.1.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  15/ 291]                blk.1.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  16/ 291]                  blk.1.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  17/ 291]                blk.1.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    86.00 MB ->    29.56 MB | hist: 
[  18/ 291]               blk.1.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  19/ 291]                blk.1.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  20/ 291]                  blk.2.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  21/ 291]                  blk.2.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  22/ 291]                  blk.2.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    32.00 MB ->    11.00 MB | hist: 
[  23/ 291]             blk.2.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  24/ 291]                blk.2.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  25/ 291]                  blk.2.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  26/ 291]                blk.2.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    86.00 MB ->    29.56 MB | hist: 
[  27/ 291]               blk.2.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  28/ 291]                blk.2.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  29/ 291]                  blk.3.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  30/ 291]                  blk.3.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  31/ 291]                  blk.3.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    32.00 MB ->    11.00 MB | hist: 
[  32/ 291]             blk.3.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  33/ 291]                blk.3.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  34/ 291]                  blk.3.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  35/ 291]                blk.3.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q5_K .. size =    86.00 MB ->    29.56 MB | hist: 
[  36/ 291]               blk.3.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  37/ 291]                blk.3.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  38/ 291]                  blk.4.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  39/ 291]                  blk.4.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  40/ 291]                  blk.4.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  41/ 291]             blk.4.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  42/ 291]                blk.4.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  43/ 291]                  blk.4.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  44/ 291]                blk.4.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  45/ 291]               blk.4.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  46/ 291]                blk.4.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  47/ 291]                  blk.5.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  48/ 291]                  blk.5.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  49/ 291]                  blk.5.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  50/ 291]             blk.5.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  51/ 291]                blk.5.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  52/ 291]                  blk.5.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  53/ 291]                blk.5.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  54/ 291]               blk.5.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  55/ 291]                blk.5.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  56/ 291]                  blk.6.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  57/ 291]                  blk.6.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  58/ 291]                  blk.6.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  59/ 291]             blk.6.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  60/ 291]                blk.6.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  61/ 291]                  blk.6.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  62/ 291]                blk.6.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  63/ 291]               blk.6.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  64/ 291]                blk.6.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  65/ 291]                  blk.7.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  66/ 291]                  blk.7.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  67/ 291]                  blk.7.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  68/ 291]             blk.7.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  69/ 291]                blk.7.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  70/ 291]                  blk.7.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  71/ 291]                blk.7.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  72/ 291]               blk.7.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  73/ 291]                blk.7.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  74/ 291]                  blk.8.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  75/ 291]                  blk.8.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  76/ 291]                  blk.8.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  77/ 291]             blk.8.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  78/ 291]                blk.8.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  79/ 291]                  blk.8.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  80/ 291]                blk.8.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  81/ 291]               blk.8.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  82/ 291]                blk.8.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  83/ 291]                  blk.9.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  84/ 291]                  blk.9.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  85/ 291]                  blk.9.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  86/ 291]             blk.9.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  87/ 291]                blk.9.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  88/ 291]                  blk.9.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  89/ 291]                blk.9.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  90/ 291]               blk.9.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  91/ 291]                blk.9.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[  92/ 291]                 blk.10.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  93/ 291]                 blk.10.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  94/ 291]                 blk.10.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  95/ 291]            blk.10.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[  96/ 291]               blk.10.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  97/ 291]                 blk.10.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  98/ 291]               blk.10.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[  99/ 291]              blk.10.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 100/ 291]               blk.10.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 101/ 291]                 blk.11.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 102/ 291]                 blk.11.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 103/ 291]                 blk.11.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 104/ 291]            blk.11.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 105/ 291]               blk.11.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 106/ 291]                 blk.11.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 107/ 291]               blk.11.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 108/ 291]              blk.11.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 109/ 291]               blk.11.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 110/ 291]                 blk.12.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 111/ 291]                 blk.12.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 112/ 291]                 blk.12.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 113/ 291]            blk.12.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 114/ 291]               blk.12.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 115/ 291]                 blk.12.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 116/ 291]               blk.12.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 117/ 291]              blk.12.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 118/ 291]               blk.12.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 119/ 291]                 blk.13.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 120/ 291]                 blk.13.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 121/ 291]                 blk.13.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 122/ 291]            blk.13.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 123/ 291]               blk.13.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 124/ 291]                 blk.13.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 125/ 291]               blk.13.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 126/ 291]              blk.13.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 127/ 291]               blk.13.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 128/ 291]                 blk.14.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 129/ 291]                 blk.14.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 130/ 291]                 blk.14.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 131/ 291]            blk.14.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 132/ 291]               blk.14.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 133/ 291]                 blk.14.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 134/ 291]               blk.14.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 135/ 291]              blk.14.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 136/ 291]               blk.14.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 137/ 291]                 blk.15.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 138/ 291]                 blk.15.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 139/ 291]                 blk.15.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 140/ 291]            blk.15.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 141/ 291]               blk.15.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 142/ 291]                 blk.15.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 143/ 291]               blk.15.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 144/ 291]              blk.15.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 145/ 291]               blk.15.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 146/ 291]                 blk.16.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 147/ 291]                 blk.16.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 148/ 291]                 blk.16.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 149/ 291]            blk.16.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 150/ 291]               blk.16.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 151/ 291]                 blk.16.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 152/ 291]               blk.16.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 153/ 291]              blk.16.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 154/ 291]               blk.16.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 155/ 291]                 blk.17.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 156/ 291]                 blk.17.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 157/ 291]                 blk.17.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 158/ 291]            blk.17.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 159/ 291]               blk.17.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 160/ 291]                 blk.17.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 161/ 291]               blk.17.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 162/ 291]              blk.17.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 163/ 291]               blk.17.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 164/ 291]                 blk.18.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 165/ 291]                 blk.18.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 166/ 291]                 blk.18.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 167/ 291]            blk.18.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 168/ 291]               blk.18.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 169/ 291]                 blk.18.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 170/ 291]               blk.18.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 171/ 291]              blk.18.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 172/ 291]               blk.18.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 173/ 291]                 blk.19.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 174/ 291]                 blk.19.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 175/ 291]                 blk.19.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 176/ 291]            blk.19.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 177/ 291]               blk.19.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 178/ 291]                 blk.19.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 179/ 291]               blk.19.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 180/ 291]              blk.19.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 181/ 291]               blk.19.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 182/ 291]                 blk.20.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 183/ 291]                 blk.20.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 184/ 291]                 blk.20.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 185/ 291]            blk.20.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 186/ 291]               blk.20.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 187/ 291]                 blk.20.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 188/ 291]               blk.20.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 189/ 291]              blk.20.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 190/ 291]               blk.20.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 191/ 291]                 blk.21.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 192/ 291]                 blk.21.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 193/ 291]                 blk.21.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 194/ 291]            blk.21.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 195/ 291]               blk.21.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 196/ 291]                 blk.21.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 197/ 291]               blk.21.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 198/ 291]              blk.21.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 199/ 291]               blk.21.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 200/ 291]                 blk.22.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 201/ 291]                 blk.22.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 202/ 291]                 blk.22.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 203/ 291]            blk.22.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 204/ 291]               blk.22.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 205/ 291]                 blk.22.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 206/ 291]               blk.22.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 207/ 291]              blk.22.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 208/ 291]               blk.22.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 209/ 291]                 blk.23.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 210/ 291]                 blk.23.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 211/ 291]                 blk.23.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 212/ 291]            blk.23.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 213/ 291]               blk.23.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 214/ 291]                 blk.23.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 215/ 291]               blk.23.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 216/ 291]              blk.23.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 217/ 291]               blk.23.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 218/ 291]                 blk.24.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 219/ 291]                 blk.24.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 220/ 291]                 blk.24.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 221/ 291]            blk.24.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 222/ 291]               blk.24.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 223/ 291]                 blk.24.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 224/ 291]               blk.24.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 225/ 291]              blk.24.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 226/ 291]               blk.24.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 227/ 291]                 blk.25.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 228/ 291]                 blk.25.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 229/ 291]                 blk.25.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 230/ 291]            blk.25.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 231/ 291]               blk.25.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 232/ 291]                 blk.25.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 233/ 291]               blk.25.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 234/ 291]              blk.25.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 235/ 291]               blk.25.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 236/ 291]                 blk.26.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 237/ 291]                 blk.26.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 238/ 291]                 blk.26.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 239/ 291]            blk.26.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 240/ 291]               blk.26.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 241/ 291]                 blk.26.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 242/ 291]               blk.26.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 243/ 291]              blk.26.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 244/ 291]               blk.26.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 245/ 291]                 blk.27.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 246/ 291]                 blk.27.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 247/ 291]                 blk.27.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 248/ 291]            blk.27.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 249/ 291]               blk.27.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 250/ 291]                 blk.27.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 251/ 291]               blk.27.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 252/ 291]              blk.27.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 253/ 291]               blk.27.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 254/ 291]                 blk.28.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 255/ 291]                 blk.28.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 256/ 291]                 blk.28.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 257/ 291]            blk.28.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 258/ 291]               blk.28.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 259/ 291]                 blk.28.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 260/ 291]               blk.28.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 261/ 291]              blk.28.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 262/ 291]               blk.28.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 263/ 291]                 blk.29.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 264/ 291]                 blk.29.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 265/ 291]                 blk.29.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 266/ 291]            blk.29.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 267/ 291]               blk.29.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 268/ 291]                 blk.29.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 269/ 291]               blk.29.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 270/ 291]              blk.29.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 271/ 291]               blk.29.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 272/ 291]                 blk.30.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 273/ 291]                 blk.30.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 274/ 291]                 blk.30.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 275/ 291]            blk.30.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 276/ 291]               blk.30.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 277/ 291]                 blk.30.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 278/ 291]               blk.30.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 279/ 291]              blk.30.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 280/ 291]               blk.30.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 281/ 291]                 blk.31.attn_q.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 282/ 291]                 blk.31.attn_k.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 283/ 291]                 blk.31.attn_v.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 284/ 291]            blk.31.attn_output.weight - [ 4096,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    32.00 MB ->     9.00 MB | hist: 
[ 285/ 291]               blk.31.ffn_gate.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 286/ 291]                 blk.31.ffn_up.weight - [ 4096, 11008,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 287/ 291]               blk.31.ffn_down.weight - [11008,  4096,     1,     1], type =    f16, quantizing to q4_K .. size =    86.00 MB ->    24.19 MB | hist: 
[ 288/ 291]              blk.31.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 289/ 291]               blk.31.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 290/ 291]                   output_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB
[ 291/ 291]                        output.weight - [ 4096, 32016,     1,     1], type =    f16, quantizing to q6_K .. size =   250.12 MB ->   102.59 MB | hist: 
llama_model_quantize_internal: model size  = 12853.27 MB
llama_model_quantize_internal: quant size  =  3677.45 MB

main: quantize time = 1089230.46 ms
main:    total time = 1089230.46 ms

Run inference

Here is a simple script to run your quantized models. I'm offloading every layer to the GPU (35 for a 7b parameter model) to speed up inference.

In [ ]:

import os

model_list = [file for file in os.listdir(MODEL_NAME) if GGML_VERSION in file]

prompt = input("Enter your prompt: ")
chosen_method = input("Please specify the quantization method to run the model (options: " + ", ".join(model_list) + "): ")

# Verify the chosen method is in the list
if chosen_method not in model_list:
    print("Invalid method chosen!")
else:
    qtype = f"{MODEL_NAME}/{MODEL_NAME.lower()}.{GGML_VERSION}.{method}.bin"
    !./llama.cpp/main -m {qtype} -n 128 --color -ngl 35 -p "{prompt}"

Enter your prompt: prompt
Please specify the quantization method to run the model (options: q4_k_s): q4_k_s
main: build = 1100 (dd0dc36)
main: seed  = 1693227123
ggml_init_cublas: found 1 CUDA devices:
  Device 0: Tesla T4, compute capability 7.5
llama_model_loader: loaded meta data with 17 key-value pairs and 291 tensors from EvolCodeLlama-7b/evolcodellama-7b.gguf.q4_k_s.bin (version GGUF V2 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q4_K     [  4096, 32016,     1,     1 ]
llama_model_loader: - tensor    1:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    2:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    6:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    9:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   10:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   11:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   15:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   19:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   20:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   24:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   28:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   29:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   33:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   37:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   38:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   42:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   46:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   47:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   51:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   55:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   56:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   60:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   64:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   65:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   69:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   73:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   74:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   78:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   82:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   83:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   87:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   91:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   92:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   96:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  100:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  101:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  105:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  109:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  110:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  114:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  118:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  119:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  123:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  127:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  128:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  132:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  136:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  137:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  145:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  146:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  150:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  154:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  155:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  159:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  163:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  164:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  168:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  172:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  173:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  177:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  181:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  182:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  186:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  190:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  191:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  195:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  199:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  200:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  204:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  208:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  209:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  213:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  217:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  218:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  222:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  226:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  227:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  231:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  235:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  236:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  240:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  244:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  245:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  249:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  253:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  254:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  258:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  262:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  263:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  267:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  271:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  272:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  276:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  280:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  281:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  285:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  289:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:                    output.weight q6_K     [  4096, 32016,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str     
llama_model_loader: - kv   1:                               general.name str     
llama_model_loader: - kv   2:                       llama.context_length u32     
llama_model_loader: - kv   3:                     llama.embedding_length u32     
llama_model_loader: - kv   4:                          llama.block_count u32     
llama_model_loader: - kv   5:                  llama.feed_forward_length u32     
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     
llama_model_loader: - kv   7:                 llama.attention.head_count u32     
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     
llama_model_loader: - kv  10:                       llama.rope.freq_base f32     
llama_model_loader: - kv  11:                          general.file_type u32     
llama_model_loader: - kv  12:                       tokenizer.ggml.model str     
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr     
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr     
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr     
llama_model_loader: - kv  16:               general.quantization_version u32     
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_K:  217 tensors
llama_model_loader: - type q5_K:    8 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_print_meta: format         = GGUF V2 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32016
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 16384
llm_load_print_meta: n_ctx          = 512
llm_load_print_meta: n_embd         = 4096
llm_load_print_meta: n_head         = 32
llm_load_print_meta: n_head_kv      = 32
llm_load_print_meta: n_layer        = 32
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: n_ff           = 11008
llm_load_print_meta: freq_base      = 1000000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 7B
llm_load_print_meta: model ftype    = mostly Q4_K - Small
llm_load_print_meta: model size     = 6.74 B
llm_load_print_meta: general.name   = LLaMA
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.09 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required  =   70.44 MB (+  256.00 MB per state)
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloading v cache to GPU
llm_load_tensors: offloading k cache to GPU
llm_load_tensors: offloaded 35/35 layers to GPU
llm_load_tensors: VRAM used: 3864 MB
..................................................................................................
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size =   71.94 MB
llama_new_context_with_model: VRAM scratch buffer: 70.53 MB

system_info: n_threads = 2 / 2 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.800000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 512, n_batch = 512, n_predict = 128, n_keep = 0


[33m prompt[0m.				
					if( !this->m_pMiscSettings ) { return; }	// If no misc settings, do nothing
					
					// Get the value of the checkbox for "Always on top"
					bool alwaysOnTop = this->m_pMiscSettings->GetBool(L"AlwaysOnTop", false);
					this->SetWindowPos((alwaysOnTop ? HWND_TOPMOST : HWND_NOTOPMOST
llama_print_timings:        load time =  1392.10 ms
llama_print_timings:      sample time =   147.99 ms /   128 runs   (    1.16 ms per token,   864.92 tokens per second)
llama_print_timings: prompt eval time =   261.80 ms /     2 tokens (  130.90 ms per token,     7.64 tokens per second)
llama_print_timings:        eval time =  5923.18 ms /   127 runs   (   46.64 ms per token,    21.44 tokens per second)
llama_print_timings:       total time =  6370.96 ms

Push to hub

To push your model to the hub, run the following blocks. It will create a new repo with the "-GGUF" suffix. Don't forget to change the username variable in the following block.

In [ ]:

!pip install -q huggingface_hub

username = "mlabonne"

from huggingface_hub import notebook_login, create_repo, HfApi
notebook_login()

[?25l     [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m0.0/268.8 kB[0m [31m?[0m eta [36m-:--:--[0m
[2K     [91m━━━━━━━━━━[0m[91m╸[0m[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m71.7/268.8 kB[0m [31m2.0 MB/s[0m eta [36m0:00:01[0m
[2K     [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m268.8/268.8 kB[0m [31m3.8 MB/s[0m eta [36m0:00:00[0m
[?25h

VBox(children=(HTML(value='<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…

In [ ]:

api = HfApi()


create_repo(repo_id = f"{username}/{MODEL_NAME}-GGUF", repo_type="model", exist_ok=True)

api.upload_folder(
    folder_path=MODEL_NAME,
    repo_id=f"{username}/{MODEL_NAME}-GGUF",
    allow_patterns=f"*{GGML_VERSION}*",
)

173 KiB Raw Blame History

Quantize Llama 2 models using ggml

Usage

Quantization methods

Run inference

Push to hub

173 KiB

Raw Blame History