Sakalti commited on
Commit
c4a25e4
1 Parent(s): 130fc4b

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +35 -0
  3. generation_config.json +8 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - qwen2
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - qwen2
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Sakalti/Saba1.5-Pro",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 256000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 151654,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "factor": 1.953125,
23
+ "type": "linear"
24
+ },
25
+ "rope_theta": 1000000.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.46.3",
30
+ "unsloth_version": "2024.12.8",
31
+ "use_cache": true,
32
+ "use_mrope": false,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 151936
35
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "max_length": 256000,
6
+ "pad_token_id": 151654,
7
+ "transformers_version": "4.46.3"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3a644270cfa3c503ebb6773fd3456c05e7e1481aa21dfb3a064230e491ffec
3
+ size 3087466808