49 lines
1.2 KiB
JSON
49 lines
1.2 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "/home/acai/workspace/llm/output/v0-20250312-165836/checkpoint-5000-merged",
|
||
|
|
"architectures": [
|
||
|
|
"Qwen2ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 896,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 4864,
|
||
|
|
"max_position_embeddings": 32768,
|
||
|
|
"max_window_layers": 21,
|
||
|
|
"model_type": "qwen2",
|
||
|
|
"num_attention_heads": 14,
|
||
|
|
"num_hidden_layers": 24,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"pad_token_id": 151643,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 8,
|
||
|
|
"block_name_to_quantize": "model.layers",
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"damp_percent": 0.1,
|
||
|
|
"desc_act": false,
|
||
|
|
"group_size": 128,
|
||
|
|
"meta": {
|
||
|
|
"quantizer": [
|
||
|
|
"optimum:1.24.0",
|
||
|
|
"auto_gptq:0.7.1"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"modules_in_block_to_quantize": null,
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"sym": true,
|
||
|
|
"true_sequential": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": 32768,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.49.0",
|
||
|
|
"use_cache": false,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|