cxdu commited on
Commit
1d4efa3
1 Parent(s): df311fb
Files changed (3) hide show
  1. config.json +35 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JackFram/llama-68m",
3
+ "architectures": [
4
+ "smallLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "block_size": 5,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "large_head_dim": 128,
15
+ "large_hidden_size": 5120,
16
+ "large_num_attention_heads": 40,
17
+ "latent_batch": 1,
18
+ "loss_margin": 0,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 1,
23
+ "num_key_value_heads": 32,
24
+ "pad_token_id": 1,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.33.3",
32
+ "use_cache": true,
33
+ "use_remap": false,
34
+ "vocab_size": 32000
35
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.33.3"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4628bbc3ba1e873be0c16118ee2cad0f96ea6dfbc342ae3a90b2dcc758d9171
3
+ size 1887490587