CyrusCheungkf/git-commit-7B-q4b
05
1{
2 "architectures": [
3 "Qwen2ForCausalLM"
4 ],
5 "attention_dropout": 0.0,
6 "bos_token_id": 151643,
7 "eos_token_id": 151645,
8 "hidden_act": "silu",
9 "hidden_size": 3584,
10 "initializer_range": 0.02,
11 "intermediate_size": 18944,
12 "max_position_embeddings": 32768,
13 "max_window_layers": 28,
14 "model_type": "qwen2",
15 "num_attention_heads": 28,
16 "num_hidden_layers": 28,
17 "num_key_value_heads": 4,
18 "quantization_config": {
19 "_load_in_4bit": true,
20 "_load_in_8bit": false,
21 "bnb_4bit_compute_dtype": "bfloat16",
22 "bnb_4bit_quant_storage": "uint8",
23 "bnb_4bit_quant_type": "fp4",
24 "bnb_4bit_use_double_quant": false,
25 "llm_int8_enable_fp32_cpu_offload": false,
26 "llm_int8_has_fp16_weight": false,
27 "llm_int8_skip_modules": null,
28 "llm_int8_threshold": 6.0,
29 "load_in_4bit": true,
30 "load_in_8bit": false,
31 "quant_method": "bitsandbytes"
32 },
33 "rms_norm_eps": 1e-06,
34 "rope_scaling": null,
35 "rope_theta": 1000000.0,
36 "sliding_window": 131072,
37 "tie_word_embeddings": false,
38 "torch_dtype": "float16",
39 "transformers_version": "4.50.2",
40 "use_cache": true,
41 "use_sliding_window": false,
42 "vocab_size": 152064
43}
44 