peter commited on
Commit
3f8082e
1 Parent(s): 9148a78
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ gptq_model-4bit-128g.safetensors filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 2560,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 10240,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "gpt_neox",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "rotary_emb_base": 10000,
18
+ "rotary_pct": 1.0,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.28.1",
22
+ "use_cache": true,
23
+ "use_parallel_residual": false,
24
+ "vocab_size": 50432
25
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": 0,
4
+ "from_model_config": false,
5
+ "max_new_tokens": 128,
6
+ "pad_token_id": 0,
7
+ "penalty_alpha": 0.6,
8
+ "temperature": 0.7,
9
+ "top_k": 4,
10
+ "transformers_version": "4.28.1"
11
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd67acbb5e1d4b63ff26567ec041208bbcdfa54a9f6b8dace4bc9f0b38d415a0
3
+ size 1962625112
quantize_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true
8
+ }
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": 2048,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }