Files changed (1) hide show
  1. config.json +0 -44
config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 32,
19
- "num_key_value_heads": 8,
20
- "pretraining_tp": 1,
21
- "quantization_config": {
22
- "_load_in_4bit": true,
23
- "_load_in_8bit": false,
24
- "bnb_4bit_compute_dtype": "bfloat16",
25
- "bnb_4bit_quant_storage": "uint8",
26
- "bnb_4bit_quant_type": "nf4",
27
- "bnb_4bit_use_double_quant": true,
28
- "llm_int8_enable_fp32_cpu_offload": false,
29
- "llm_int8_has_fp16_weight": false,
30
- "llm_int8_skip_modules": null,
31
- "llm_int8_threshold": 6.0,
32
- "load_in_4bit": true,
33
- "load_in_8bit": false,
34
- "quant_method": "bitsandbytes"
35
- },
36
- "rms_norm_eps": 1e-05,
37
- "rope_scaling": null,
38
- "rope_theta": 500000.0,
39
- "tie_word_embeddings": false,
40
- "torch_dtype": "bfloat16",
41
- "transformers_version": "4.41.0",
42
- "use_cache": true,
43
- "vocab_size": 128256
44
- }