konbraphat51 commited on
Commit
934b641
1 Parent(s): 537a968

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +40 -0
  2. generation_config.json +6 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cyberagent/open-calm-1b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "float32",
22
+ "bnb_4bit_quant_type": "fp4",
23
+ "bnb_4bit_use_double_quant": false,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": false,
29
+ "load_in_8bit": true
30
+ },
31
+ "rope_scaling": null,
32
+ "rotary_emb_base": 10000,
33
+ "rotary_pct": 1.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.31.0",
37
+ "use_cache": true,
38
+ "use_parallel_residual": false,
39
+ "vocab_size": 52096
40
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.31.0"
6
+ }