41 lines
1.0 KiB
JSON
41 lines
1.0 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "/mnt/nas2/huangjintao.hjt/.cache/modelscope/hub/qwen/CodeQwen1___5-7B-Chat",
|
||
|
|
"architectures": [
|
||
|
|
"Qwen2ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 2,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 13440,
|
||
|
|
"max_position_embeddings": 65536,
|
||
|
|
"max_window_layers": 28,
|
||
|
|
"model_type": "qwen2",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"damp_percent": 0.1,
|
||
|
|
"desc_act": false,
|
||
|
|
"group_size": 128,
|
||
|
|
"modules_in_block_to_quantize": null,
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"sym": true,
|
||
|
|
"true_sequential": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_theta": 1000000,
|
||
|
|
"rotary_emb_base": 1000000,
|
||
|
|
"seq_length": 65536,
|
||
|
|
"sliding_window": 65536,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.39.3",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 92416
|
||
|
|
}
|