Agnuxo commited on
Commit
9da45a7
1 Parent(s): dad5f73

Trained with Unsloth

Browse files
Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +31 -0
  3. generation_config.json +8 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - unsloth
10
  - llama
11
  - trl
 
12
  ---
13
 
14
  # Uploaded model
 
9
  - unsloth
10
  - llama
11
  - trl
12
+ - sft
13
  ---
14
 
15
  # Uploaded model
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "reciprocate/tiny-llama",
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": 64,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 64,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 1,
18
+ "num_hidden_layers": 1,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.43.4",
28
+ "unsloth_version": "2024.8",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 2048,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.43.4"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0cdfb533ceb30880019f5e818eda83f65cb7eac993f1896b82ca6c3c1d30b4
3
+ size 8250984