|
{ |
|
"vocab_size": 32256, |
|
"max_position_embeddings": 16384, |
|
"hidden_size": 7168, |
|
"intermediate_size": 19200, |
|
"num_hidden_layers": 62, |
|
"num_attention_heads": 56, |
|
"num_key_value_heads": 8, |
|
"hidden_act": "silu", |
|
"initializer_range": 0.02, |
|
"rms_norm_eps": 1e-06, |
|
"pretraining_tp": 1, |
|
"use_cache": true, |
|
"rope_theta": 100000, |
|
"rope_scaling": { |
|
"factor": 4.0, |
|
"type": "linear" |
|
}, |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"torch_dtype": "float16", |
|
"tie_word_embeddings": false, |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"bos_token_id": 32013, |
|
"eos_token_id": 32014, |
|
"_name_or_path": "deepseek-ai/deepseek-coder-33b-base", |
|
"transformers_version": "4.38.2", |
|
"model_type": "llama", |
|
"quantization_config": { |
|
"quant_method": "aqlm", |
|
"nbits_per_codebook": 16, |
|
"num_codebooks": 1, |
|
"out_group_size": 1, |
|
"in_group_size": 8, |
|
"linear_weights_not_to_quantize": [ |
|
"model.layers.0.input_layernorm.weight", |
|
"model.layers.0.post_attention_layernorm.weight", |
|
"model.layers.1.input_layernorm.weight", |
|
"model.layers.1.post_attention_layernorm.weight", |
|
"model.layers.2.input_layernorm.weight", |
|
"model.layers.2.post_attention_layernorm.weight", |
|
"model.layers.3.input_layernorm.weight", |
|
"model.layers.3.post_attention_layernorm.weight", |
|
"model.layers.4.input_layernorm.weight", |
|
"model.layers.4.post_attention_layernorm.weight", |
|
"model.layers.5.input_layernorm.weight", |
|
"model.layers.5.post_attention_layernorm.weight", |
|
"model.layers.6.input_layernorm.weight", |
|
"model.layers.6.post_attention_layernorm.weight", |
|
"model.layers.7.input_layernorm.weight", |
|
"model.layers.7.post_attention_layernorm.weight", |
|
"model.layers.8.input_layernorm.weight", |
|
"model.layers.8.post_attention_layernorm.weight", |
|
"model.layers.9.input_layernorm.weight", |
|
"model.layers.9.post_attention_layernorm.weight", |
|
"model.layers.10.input_layernorm.weight", |
|
"model.layers.10.post_attention_layernorm.weight", |
|
"model.layers.11.input_layernorm.weight", |
|
"model.layers.11.post_attention_layernorm.weight", |
|
"model.layers.12.input_layernorm.weight", |
|
"model.layers.12.post_attention_layernorm.weight", |
|
"model.layers.13.input_layernorm.weight", |
|
"model.layers.13.post_attention_layernorm.weight", |
|
"model.layers.14.input_layernorm.weight", |
|
"model.layers.14.post_attention_layernorm.weight", |
|
"model.layers.15.input_layernorm.weight", |
|
"model.layers.15.post_attention_layernorm.weight", |
|
"model.layers.16.input_layernorm.weight", |
|
"model.layers.16.post_attention_layernorm.weight", |
|
"model.layers.17.input_layernorm.weight", |
|
"model.layers.17.post_attention_layernorm.weight", |
|
"model.layers.18.input_layernorm.weight", |
|
"model.layers.18.post_attention_layernorm.weight", |
|
"model.layers.19.input_layernorm.weight", |
|
"model.layers.19.post_attention_layernorm.weight", |
|
"model.layers.20.input_layernorm.weight", |
|
"model.layers.20.post_attention_layernorm.weight", |
|
"model.layers.21.input_layernorm.weight", |
|
"model.layers.21.post_attention_layernorm.weight", |
|
"model.layers.22.input_layernorm.weight", |
|
"model.layers.22.post_attention_layernorm.weight", |
|
"model.layers.23.input_layernorm.weight", |
|
"model.layers.23.post_attention_layernorm.weight", |
|
"model.layers.24.input_layernorm.weight", |
|
"model.layers.24.post_attention_layernorm.weight", |
|
"model.layers.25.input_layernorm.weight", |
|
"model.layers.25.post_attention_layernorm.weight", |
|
"model.layers.26.input_layernorm.weight", |
|
"model.layers.26.post_attention_layernorm.weight", |
|
"model.layers.27.input_layernorm.weight", |
|
"model.layers.27.post_attention_layernorm.weight", |
|
"model.layers.28.input_layernorm.weight", |
|
"model.layers.28.post_attention_layernorm.weight", |
|
"model.layers.29.input_layernorm.weight", |
|
"model.layers.29.post_attention_layernorm.weight", |
|
"model.layers.30.input_layernorm.weight", |
|
"model.layers.30.post_attention_layernorm.weight", |
|
"model.layers.31.input_layernorm.weight", |
|
"model.layers.31.post_attention_layernorm.weight", |
|
"model.layers.32.input_layernorm.weight", |
|
"model.layers.32.post_attention_layernorm.weight", |
|
"model.layers.33.input_layernorm.weight", |
|
"model.layers.33.post_attention_layernorm.weight", |
|
"model.layers.34.input_layernorm.weight", |
|
"model.layers.34.post_attention_layernorm.weight", |
|
"model.layers.35.input_layernorm.weight", |
|
"model.layers.35.post_attention_layernorm.weight", |
|
"model.layers.36.input_layernorm.weight", |
|
"model.layers.36.post_attention_layernorm.weight", |
|
"model.layers.37.input_layernorm.weight", |
|
"model.layers.37.post_attention_layernorm.weight", |
|
"model.layers.38.input_layernorm.weight", |
|
"model.layers.38.post_attention_layernorm.weight", |
|
"model.layers.39.input_layernorm.weight", |
|
"model.layers.39.post_attention_layernorm.weight", |
|
"model.layers.40.input_layernorm.weight", |
|
"model.layers.40.post_attention_layernorm.weight", |
|
"model.layers.41.input_layernorm.weight", |
|
"model.layers.41.post_attention_layernorm.weight", |
|
"model.layers.42.input_layernorm.weight", |
|
"model.layers.42.post_attention_layernorm.weight", |
|
"model.layers.43.input_layernorm.weight", |
|
"model.layers.43.post_attention_layernorm.weight", |
|
"model.layers.44.input_layernorm.weight", |
|
"model.layers.44.post_attention_layernorm.weight", |
|
"model.layers.45.input_layernorm.weight", |
|
"model.layers.45.post_attention_layernorm.weight", |
|
"model.layers.46.input_layernorm.weight", |
|
"model.layers.46.post_attention_layernorm.weight", |
|
"model.layers.47.input_layernorm.weight", |
|
"model.layers.47.post_attention_layernorm.weight", |
|
"model.layers.48.input_layernorm.weight", |
|
"model.layers.48.post_attention_layernorm.weight", |
|
"model.layers.49.input_layernorm.weight", |
|
"model.layers.49.post_attention_layernorm.weight", |
|
"model.layers.50.input_layernorm.weight", |
|
"model.layers.50.post_attention_layernorm.weight", |
|
"model.layers.51.input_layernorm.weight", |
|
"model.layers.51.post_attention_layernorm.weight", |
|
"model.layers.52.input_layernorm.weight", |
|
"model.layers.52.post_attention_layernorm.weight", |
|
"model.layers.53.input_layernorm.weight", |
|
"model.layers.53.post_attention_layernorm.weight", |
|
"model.layers.54.input_layernorm.weight", |
|
"model.layers.54.post_attention_layernorm.weight", |
|
"model.layers.55.input_layernorm.weight", |
|
"model.layers.55.post_attention_layernorm.weight", |
|
"model.layers.56.input_layernorm.weight", |
|
"model.layers.56.post_attention_layernorm.weight", |
|
"model.layers.57.input_layernorm.weight", |
|
"model.layers.57.post_attention_layernorm.weight", |
|
"model.layers.58.input_layernorm.weight", |
|
"model.layers.58.post_attention_layernorm.weight", |
|
"model.layers.59.input_layernorm.weight", |
|
"model.layers.59.post_attention_layernorm.weight", |
|
"model.layers.60.input_layernorm.weight", |
|
"model.layers.60.post_attention_layernorm.weight", |
|
"model.layers.61.input_layernorm.weight", |
|
"model.layers.61.post_attention_layernorm.weight", |
|
"model.embed_tokens.weight", |
|
"model.norm.weight", |
|
"lm_head.weight" |
|
] |
|
} |
|
} |