myst72 commited on
Commit
0dee000
·
verified ·
1 Parent(s): 383c412

Upload LlamaForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. config.json +30 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
7
 
8
  # Model Card for Model ID
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "infly/OpenCoder-1.5B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 96540,
9
+ "eos_token_id": 96539,
10
+ "head_dim": 160,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2240,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 14,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 14,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.47.1",
28
+ "use_cache": true,
29
+ "vocab_size": 96640
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 96540,
4
+ "eos_token_id": 96539,
5
+ "transformers_version": "4.47.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a73cb864ad1d406a949163d18b852f7e5cf323d075033d4f329a7c53d9dc74
3
+ size 3811327120