rockerBOO commited on
Commit
be70420
1 Parent(s): 99386c9

Add int8 model

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stablelm-tuned-alpha-3b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 16,
18
+ "quantization_config": {
19
+ "llm_int8_enable_fp32_cpu_offload": false,
20
+ "llm_int8_skip_modules": null,
21
+ "llm_int8_threshold": 6.0,
22
+ "load_in_8bit": true
23
+ },
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.29.2",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50688
32
+ }
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": "4.29.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5b0011107cb2d543702e2497affe0f35acf115741d34916b8aec1e19ff953a
3
+ size 4324316537
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }