46 lines
1.1 KiB
JSON
46 lines
1.1 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "./tmp_autoround_awq",
|
||
|
|
"architectures": [
|
||
|
|
"Qwen2ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"eos_token_id": 151643,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1536,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8960,
|
||
|
|
"max_position_embeddings": 131072,
|
||
|
|
"max_window_layers": 21,
|
||
|
|
"model_type": "qwen2",
|
||
|
|
"num_attention_heads": 12,
|
||
|
|
"num_hidden_layers": 28,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"quantization_config": {
|
||
|
|
"backend": "autoawq",
|
||
|
|
"bits": 4,
|
||
|
|
"do_fuse": false,
|
||
|
|
"exllama_config": null,
|
||
|
|
"fuse_max_seq_len": null,
|
||
|
|
"group_size": 128,
|
||
|
|
"modules_to_fuse": null,
|
||
|
|
"modules_to_not_convert": [
|
||
|
|
"lm_head"
|
||
|
|
],
|
||
|
|
"quant_method": "awq",
|
||
|
|
"version": "gemm",
|
||
|
|
"zero_point": false
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.47.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_mrope": false,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|