ISTA-DASLab/c4ai-command-r-plus-AQLM-2Bit-1x16
1093
1{2 "_name_or_path": "/slot/sandbox/j/_tmp/data1yx_lw9k",3 "architectures": [4 "CohereForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 5,9 "eos_token_id": 255001,10 "hidden_act": "silu",11 "hidden_size": 12288,12 "initializer_range": 0.02,13 "intermediate_size": 33792,14 "layer_norm_eps": 1e-05,15 "logit_scale": 0.8333333333333334,16 "max_position_embeddings": 8192,17 "model_max_length": 131072,18 "model_type": "cohere",19 "num_attention_heads": 96,20 "num_hidden_layers": 64,21 "num_key_value_heads": 8,22 "pad_token_id": 0,23 "quantization_config": {24 "in_group_size": 8,25 "linear_weights_not_to_quantize": [26 "model.layers.0.self_attn.q_norm.weight",27 "model.layers.0.self_attn.k_norm.weight",28 "model.layers.0.input_layernorm.weight",29 "model.layers.1.self_attn.q_norm.weight",30 "model.layers.1.self_attn.k_norm.weight",31 "model.layers.1.input_layernorm.weight",32 "model.layers.2.self_attn.q_norm.weight",33 "model.layers.2.self_attn.k_norm.weight",34 "model.layers.2.input_layernorm.weight",35 "model.layers.3.self_attn.q_norm.weight",36 "model.layers.3.self_attn.k_norm.weight",37 "model.layers.3.input_layernorm.weight",38 "model.layers.4.self_attn.q_norm.weight",39 "model.layers.4.self_attn.k_norm.weight",40 "model.layers.4.input_layernorm.weight",41 "model.layers.5.self_attn.q_norm.weight",42 "model.layers.5.self_attn.k_norm.weight",43 "model.layers.5.input_layernorm.weight",44 "model.layers.6.self_attn.q_norm.weight",45 "model.layers.6.self_attn.k_norm.weight",46 "model.layers.6.input_layernorm.weight",47 "model.layers.7.self_attn.q_norm.weight",48 "model.layers.7.self_attn.k_norm.weight",49 "model.layers.7.input_layernorm.weight",50 "model.layers.8.self_attn.q_norm.weight",51 "model.layers.8.self_attn.k_norm.weight",52 "model.layers.8.input_layernorm.weight",53 "model.layers.9.self_attn.q_norm.weight",54 "model.layers.9.self_attn.k_norm.weight",55 "model.layers.9.input_layernorm.weight",56 "model.layers.10.self_attn.q_norm.weight",57 "model.layers.10.self_attn.k_norm.weight",58 "model.layers.10.input_layernorm.weight",59 "model.layers.11.self_attn.q_norm.weight",60 "model.layers.11.self_attn.k_norm.weight",61 "model.layers.11.input_layernorm.weight",62 "model.layers.12.self_attn.q_norm.weight",63 "model.layers.12.self_attn.k_norm.weight",64 "model.layers.12.input_layernorm.weight",65 "model.layers.13.self_attn.q_norm.weight",66 "model.layers.13.self_attn.k_norm.weight",67 "model.layers.13.input_layernorm.weight",68 "model.layers.14.self_attn.q_norm.weight",69 "model.layers.14.self_attn.k_norm.weight",70 "model.layers.14.input_layernorm.weight",71 "model.layers.15.self_attn.q_norm.weight",72 "model.layers.15.self_attn.k_norm.weight",73 "model.layers.15.input_layernorm.weight",74 "model.layers.16.self_attn.q_norm.weight",75 "model.layers.16.self_attn.k_norm.weight",76 "model.layers.16.input_layernorm.weight",77 "model.layers.17.self_attn.q_norm.weight",78 "model.layers.17.self_attn.k_norm.weight",79 "model.layers.17.input_layernorm.weight",80 "model.layers.18.self_attn.q_norm.weight",81 "model.layers.18.self_attn.k_norm.weight",82 "model.layers.18.input_layernorm.weight",83 "model.layers.19.self_attn.q_norm.weight",84 "model.layers.19.self_attn.k_norm.weight",85 "model.layers.19.input_layernorm.weight",86 "model.layers.20.self_attn.q_norm.weight",87 "model.layers.20.self_attn.k_norm.weight",88 "model.layers.20.input_layernorm.weight",89 "model.layers.21.self_attn.q_norm.weight",90 "model.layers.21.self_attn.k_norm.weight",91 "model.layers.21.input_layernorm.weight",92 "model.layers.22.self_attn.q_norm.weight",93 "model.layers.22.self_attn.k_norm.weight",94 "model.layers.22.input_layernorm.weight",95 "model.layers.23.self_attn.q_norm.weight",96 "model.layers.23.self_attn.k_norm.weight",97 "model.layers.23.input_layernorm.weight",98 "model.layers.24.self_attn.q_norm.weight",99 "model.layers.24.self_attn.k_norm.weight",100 "model.layers.24.input_layernorm.weight",101 "model.layers.25.self_attn.q_norm.weight",102 "model.layers.25.self_attn.k_norm.weight",103 "model.layers.25.input_layernorm.weight",104 "model.layers.26.self_attn.q_norm.weight",105 "model.layers.26.self_attn.k_norm.weight",106 "model.layers.26.input_layernorm.weight",107 "model.layers.27.self_attn.q_norm.weight",108 "model.layers.27.self_attn.k_norm.weight",109 "model.layers.27.input_layernorm.weight",110 "model.layers.28.self_attn.q_norm.weight",111 "model.layers.28.self_attn.k_norm.weight",112 "model.layers.28.input_layernorm.weight",113 "model.layers.29.self_attn.q_norm.weight",114 "model.layers.29.self_attn.k_norm.weight",115 "model.layers.29.input_layernorm.weight",116 "model.layers.30.self_attn.q_norm.weight",117 "model.layers.30.self_attn.k_norm.weight",118 "model.layers.30.input_layernorm.weight",119 "model.layers.31.self_attn.q_norm.weight",120 "model.layers.31.self_attn.k_norm.weight",121 "model.layers.31.input_layernorm.weight",122 "model.layers.32.self_attn.q_norm.weight",123 "model.layers.32.self_attn.k_norm.weight",124 "model.layers.32.input_layernorm.weight",125 "model.layers.33.self_attn.q_norm.weight",126 "model.layers.33.self_attn.k_norm.weight",127 "model.layers.33.input_layernorm.weight",128 "model.layers.34.self_attn.q_norm.weight",129 "model.layers.34.self_attn.k_norm.weight",130 "model.layers.34.input_layernorm.weight",131 "model.layers.35.self_attn.q_norm.weight",132 "model.layers.35.self_attn.k_norm.weight",133 "model.layers.35.input_layernorm.weight",134 "model.layers.36.self_attn.q_norm.weight",135 "model.layers.36.self_attn.k_norm.weight",136 "model.layers.36.input_layernorm.weight",137 "model.layers.37.self_attn.q_norm.weight",138 "model.layers.37.self_attn.k_norm.weight",139 "model.layers.37.input_layernorm.weight",140 "model.layers.38.self_attn.q_norm.weight",141 "model.layers.38.self_attn.k_norm.weight",142 "model.layers.38.input_layernorm.weight",143 "model.layers.39.self_attn.q_norm.weight",144 "model.layers.39.self_attn.k_norm.weight",145 "model.layers.39.input_layernorm.weight",146 "model.layers.40.self_attn.q_norm.weight",147 "model.layers.40.self_attn.k_norm.weight",148 "model.layers.40.input_layernorm.weight",149 "model.layers.41.self_attn.q_norm.weight",150 "model.layers.41.self_attn.k_norm.weight",151 "model.layers.41.input_layernorm.weight",152 "model.layers.42.self_attn.q_norm.weight",153 "model.layers.42.self_attn.k_norm.weight",154 "model.layers.42.input_layernorm.weight",155 "model.layers.43.self_attn.q_norm.weight",156 "model.layers.43.self_attn.k_norm.weight",157 "model.layers.43.input_layernorm.weight",158 "model.layers.44.self_attn.q_norm.weight",159 "model.layers.44.self_attn.k_norm.weight",160 "model.layers.44.input_layernorm.weight",161 "model.layers.45.self_attn.q_norm.weight",162 "model.layers.45.self_attn.k_norm.weight",163 "model.layers.45.input_layernorm.weight",164 "model.layers.46.self_attn.q_norm.weight",165 "model.layers.46.self_attn.k_norm.weight",166 "model.layers.46.input_layernorm.weight",167 "model.layers.47.self_attn.q_norm.weight",168 "model.layers.47.self_attn.k_norm.weight",169 "model.layers.47.input_layernorm.weight",170 "model.layers.48.self_attn.q_norm.weight",171 "model.layers.48.self_attn.k_norm.weight",172 "model.layers.48.input_layernorm.weight",173 "model.layers.49.self_attn.q_norm.weight",174 "model.layers.49.self_attn.k_norm.weight",175 "model.layers.49.input_layernorm.weight",176 "model.layers.50.self_attn.q_norm.weight",177 "model.layers.50.self_attn.k_norm.weight",178 "model.layers.50.input_layernorm.weight",179 "model.layers.51.self_attn.q_norm.weight",180 "model.layers.51.self_attn.k_norm.weight",181 "model.layers.51.input_layernorm.weight",182 "model.layers.52.self_attn.q_norm.weight",183 "model.layers.52.self_attn.k_norm.weight",184 "model.layers.52.input_layernorm.weight",185 "model.layers.53.self_attn.q_norm.weight",186 "model.layers.53.self_attn.k_norm.weight",187 "model.layers.53.input_layernorm.weight",188 "model.layers.54.self_attn.q_norm.weight",189 "model.layers.54.self_attn.k_norm.weight",190 "model.layers.54.input_layernorm.weight",191 "model.layers.55.self_attn.q_norm.weight",192 "model.layers.55.self_attn.k_norm.weight",193 "model.layers.55.input_layernorm.weight",194 "model.layers.56.self_attn.q_norm.weight",195 "model.layers.56.self_attn.k_norm.weight",196 "model.layers.56.input_layernorm.weight",197 "model.layers.57.self_attn.q_norm.weight",198 "model.layers.57.self_attn.k_norm.weight",199 "model.layers.57.input_layernorm.weight",200 "model.layers.58.self_attn.q_norm.weight",201 "model.layers.58.self_attn.k_norm.weight",202 "model.layers.58.input_layernorm.weight",203 "model.layers.59.self_attn.q_norm.weight",204 "model.layers.59.self_attn.k_norm.weight",205 "model.layers.59.input_layernorm.weight",206 "model.layers.60.self_attn.q_norm.weight",207 "model.layers.60.self_attn.k_norm.weight",208 "model.layers.60.input_layernorm.weight",209 "model.layers.61.self_attn.q_norm.weight",210 "model.layers.61.self_attn.k_norm.weight",211 "model.layers.61.input_layernorm.weight",212 "model.layers.62.self_attn.q_norm.weight",213 "model.layers.62.self_attn.k_norm.weight",214 "model.layers.62.input_layernorm.weight",215 "model.layers.63.self_attn.q_norm.weight",216 "model.layers.63.self_attn.k_norm.weight",217 "model.layers.63.input_layernorm.weight",218 "model.embed_tokens.weight",219 "model.norm.weight",220 "lm_head.weight"221 ],222 "nbits_per_codebook": 16,223 "num_codebooks": 1,224 "out_group_size": 1,225 "quant_method": "aqlm"226 },227 "rope_theta": 75000000.0,228 "torch_dtype": "float16",229 "transformers_version": "4.40.0.dev0",230 "use_cache": true,231 "use_qk_norm": true,232 "vocab_size": 256000233}234 