File size: 1,274 Bytes
b686dd8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
{
"_attn_implementation_autoset": true,
"_name_or_path": "/data/DeepSeek-R1-Distill-Qwen-7B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"desc_act": true,
"dynamic": null,
"group_size": 32,
"lm_head": false,
"meta": {
"damp_auto_increment": 0.0025,
"damp_percent": 0.1,
"quantizer": [
"gptqmodel:1.7.4"
],
"static_groups": false,
"true_sequential": true,
"uri": "https://github.com/modelcloud/gptqmodel"
},
"quant_method": "gptq",
"sym": true
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0.dev0",
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}
|