TrgTuan10 commited on
Commit
efa0bb0
1 Parent(s): ac79502

Training in progress, step 1000

Browse files
Files changed (3) hide show
  1. config.json +29 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-135M",
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
+ "hidden_act": "silu",
11
+ "hidden_size": 576,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 9,
18
+ "num_hidden_layers": 30,
19
+ "num_key_value_heads": 3,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.43.2",
27
+ "use_cache": true,
28
+ "vocab_size": 49152
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f626246ae962fde8692787c4576219bb6c7879c2379b7f67ca4f4415cbda8816
3
+ size 538090408
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba779f2410a06231901e69ba8b7f6ce7d13971c2a03d08409552eb7c3e905b6
3
+ size 5240