dahara1 commited on
Commit
7b78126
1 Parent(s): 1784a87
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "matsuo-lab/weblab-10b-instruction-sft",
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": 4864,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 19456,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 38,
19
+ "num_hidden_layers": 36,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.31.0",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50277
29
+ }
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": null,
9
+ "model_file_base_name": null
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1024,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }