Trisert commited on
Commit
7396aa9
1 Parent(s): 7a335d9

Upload LlamaForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +33 -0
  3. generation_config.json +7 -0
  4. pytorch_model.bin +3 -0
README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - llama
10
  - trl
 
11
  base_model: unsloth/tinyllama-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - llama
10
  - trl
11
+ - sft
12
  base_model: unsloth/tinyllama-bnb-4bit
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/tinyllama-bnb-4bit",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 2.0,
24
+ "type": "linear"
25
+ },
26
+ "rope_theta": 10000.0,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.37.2",
30
+ "unsloth_version": "2024.2",
31
+ "use_cache": true,
32
+ "vocab_size": 32000
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.2"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b36fae62888f8130aa18199ac39bacf35872b19cc75044e789b28cad6346f9
3
+ size 2200164718