amin commited on
Commit
4f56ca2
1 Parent(s): 1f65019

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +30 -0
  2. model.safetensors +3 -0
  3. rng_state.pth +3 -0
  4. tokenizer.json +0 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/dousti_group/ghanizadeh/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-135M/snapshots/1d461723eec654e65efdc40cf49301c89c0c92f4",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "pad_token_id": 1,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 128,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.43.4",
28
+ "use_cache": true,
29
+ "vocab_size": 32001
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df6ccc54866536499091d77dbaab48d7e7156fbbc0d00fe8446b828dcb84c21
3
+ size 498574472
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
+ size 14244
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff