dahara1 commited on
Commit
859dc22
·
verified ·
1 Parent(s): 71fd7bb

Delete config.json

Browse files
Files changed (1) hide show
  1. config.json +0 -52
config.json DELETED
@@ -1,52 +0,0 @@
1
- {
2
- "_name_or_path": "Meta-Llama-3.1-8B-Instruct",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "hidden_act": "silu",
15
- "hidden_size": 4096,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 14336,
18
- "max_position_embeddings": 131072,
19
- "mlp_bias": false,
20
- "model_type": "llama",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 32,
23
- "num_key_value_heads": 8,
24
- "pretraining_tp": 1,
25
- "quantization_config": {
26
- "backend": "llm-awq",
27
- "bits": 4,
28
- "do_fuse": false,
29
- "exllama_config": null,
30
- "fuse_max_seq_len": null,
31
- "group_size": 128,
32
- "modules_to_fuse": null,
33
- "modules_to_not_convert": null,
34
- "quant_method": "awq",
35
- "version": "gemv",
36
- "zero_point": true
37
- },
38
- "rms_norm_eps": 1e-05,
39
- "rope_scaling": {
40
- "factor": 8.0,
41
- "high_freq_factor": 4.0,
42
- "low_freq_factor": 1.0,
43
- "original_max_position_embeddings": 8192,
44
- "rope_type": "llama3"
45
- },
46
- "rope_theta": 500000.0,
47
- "tie_word_embeddings": false,
48
- "torch_dtype": "bfloat16",
49
- "transformers_version": "4.43.2",
50
- "use_cache": true,
51
- "vocab_size": 128256
52
- }