kskathe commited on
Commit
4d4019e
1 Parent(s): 802e3e5

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": "kskathe/llama-3.1-text-summarization",
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": 131072,
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
- "pad_token_id": 128004,
21
- "pretraining_tp": 1,
22
- "quantization_config": {
23
- "_load_in_4bit": true,
24
- "_load_in_8bit": false,
25
- "bnb_4bit_compute_dtype": "bfloat16",
26
- "bnb_4bit_quant_storage": "uint8",
27
- "bnb_4bit_quant_type": "nf4",
28
- "bnb_4bit_use_double_quant": true,
29
- "llm_int8_enable_fp32_cpu_offload": false,
30
- "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
32
- "llm_int8_threshold": 6.0,
33
- "load_in_4bit": true,
34
- "load_in_8bit": false,
35
- "quant_method": "bitsandbytes"
36
- },
37
- "rms_norm_eps": 1e-05,
38
- "rope_scaling": {
39
- "factor": 8.0,
40
- "high_freq_factor": 4.0,
41
- "low_freq_factor": 1.0,
42
- "original_max_position_embeddings": 8192,
43
- "rope_type": "llama3"
44
- },
45
- "rope_theta": 500000.0,
46
- "tie_word_embeddings": false,
47
- "torch_dtype": "bfloat16",
48
- "transformers_version": "4.44.2",
49
- "unsloth_version": "2024.9",
50
- "use_cache": true,
51
- "vocab_size": 128256
52
- }