RichardErkhov commited on
Commit
2a43403
·
verified ·
1 Parent(s): e434268

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +47 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FIN_Yi6B_DOW30_GK1506",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "_load_in_4bit": false,
25
+ "_load_in_8bit": true,
26
+ "bnb_4bit_compute_dtype": "float32",
27
+ "bnb_4bit_quant_storage": "uint8",
28
+ "bnb_4bit_quant_type": "fp4",
29
+ "bnb_4bit_use_double_quant": false,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": false,
35
+ "load_in_8bit": true,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 5000000.0,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.47.1",
44
+ "unsloth_version": "2024.8",
45
+ "use_cache": true,
46
+ "vocab_size": 64000
47
+ }