38 lines
908 B
JSON
38 lines
908 B
JSON
|
{
|
||
|
|
"_name_or_path": "/workspace/process/deepseek-ai_deepseek-coder-33b-instruct/source",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"bos_token_id": 32013,
|
||
|
|
"eos_token_id": 32021,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 7168,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 19200,
|
||
|
|
"max_position_embeddings": 16384,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 56,
|
||
|
|
"num_hidden_layers": 62,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 4.0,
|
||
|
|
"type": "linear"
|
||
|
|
},
|
||
|
|
"rope_theta": 100000,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.35.0",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 32256,
|
||
|
|
"quantization_config": {
|
||
|
|
"quant_method": "awq",
|
||
|
|
"zero_point": true,
|
||
|
|
"group_size": 128,
|
||
|
|
"bits": 4,
|
||
|
|
"version": "gemm"
|
||
|
|
}
|
||
|
|
}
|