RichardErkhov commited on
Commit
d92e89c
1 Parent(s): 43c29c1

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stablelm-2-1_6b",
3
+ "architectures": [
4
+ "StableLmForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "stablelm",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 32,
20
+ "partial_rotary_factor": 0.25,
21
+ "quantization_config": {
22
+ "_load_in_4bit": false,
23
+ "_load_in_8bit": true,
24
+ "bnb_4bit_compute_dtype": "float32",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
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": false,
33
+ "load_in_8bit": true,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.39.3",
41
+ "use_cache": true,
42
+ "use_qkv_bias": true,
43
+ "vocab_size": 100352
44
+ }