Meforgers commited on
Commit
91773b5
1 Parent(s): dd683bd

Delete config.json

Browse files
Files changed (1) hide show
  1. config.json +0 -43
config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "_name_or_path": "Qwen/Qwen2-72B-Instruct",
3
- "architectures": [
4
- "Qwen2ForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 8192,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 29568,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 80,
15
- "model_type": "qwen2",
16
- "num_attention_heads": 64,
17
- "num_hidden_layers": 80,
18
- "num_key_value_heads": 8,
19
- "quantization_config": {
20
- "_load_in_4bit": true,
21
- "_load_in_8bit": false,
22
- "bnb_4bit_compute_dtype": "bfloat16",
23
- "bnb_4bit_quant_storage": "uint8",
24
- "bnb_4bit_quant_type": "nf4",
25
- "bnb_4bit_use_double_quant": true,
26
- "llm_int8_enable_fp32_cpu_offload": false,
27
- "llm_int8_has_fp16_weight": false,
28
- "llm_int8_skip_modules": null,
29
- "llm_int8_threshold": 6.0,
30
- "load_in_4bit": true,
31
- "load_in_8bit": false,
32
- "quant_method": "bitsandbytes"
33
- },
34
- "rms_norm_eps": 1e-06,
35
- "rope_theta": 1000000.0,
36
- "sliding_window": 131072,
37
- "tie_word_embeddings": false,
38
- "torch_dtype": "bfloat16",
39
- "transformers_version": "4.41.2",
40
- "use_cache": true,
41
- "use_sliding_window": false,
42
- "vocab_size": 152064
43
- }