Hugging Face's logo

SparseLLM
/
swiglu-85B

Transformers
PyTorch
Safetensors
Model card Files
xet
 Community
Yixin Song commited on
Commit
7679c2d
·
1 Parent(s): 270c107

85B

Browse files
Files changed (10) hide show
  1. .gitattributes +9 -0
  2. README.md +3 -3
  3. config.json +3 -27
  4. generation_config.json +3 -0
  5. model.safetensors +3 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +3 -0
  8. tokenizer.json +3 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ generation_config.json filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
40
+ config.json filter=lfs diff=lfs merge=lfs -text
41
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
42
+ README.md filter=lfs diff=lfs merge=lfs -text
43
+ special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
44
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,3 @@
1
- ---
2
- license: mit
3
- ---
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0e15fa0c5cc81675bd69af8eb469d128a725c1a7bfc71f03b7877b7b650567
3
+ size 21
config.json CHANGED
@@ -1,27 +1,3 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 2048,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 5376,
13
- "max_position_embeddings": 2048,
14
- "model_type": "llama",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 24,
17
- "num_key_value_heads": 32,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "rope_theta": 10000.0,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.36.2",
25
- "use_cache": false,
26
- "vocab_size": 32000
27
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773442d8589e6f6174eca2bc52821cec241d7caf41d3be4d7d2e03dcc690ba43
3
+ size 638
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200440eaf7b79af5558225b57dc8fc7cee3e3caf149f64f694e1c0ada4f643c1
3
+ size 133
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb8ffc88b66667d0bdfce2947814aab97894b1533e3fab4b4cbeca38d61d3c5
3
+ size 2653123240
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c3303f9281c7a88e2014b6992f17e38a44c7e4fd610cfd336717f158cfa31b
3
+ size 2653215926
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa06efa2785e450051989a6f8fb4416b10149ded485ddd3f127a40734f5cfd0
3
+ size 414
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc
3
+ size 1795303
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747ec99bae3fd9d7bf9c3b9172e5ca0d82ca0d23d64a58ef1752b612f196817b
3
+ size 967