adibvafa commited on
Commit
b38f815
·
verified ·
1 Parent(s): 02a6ff5

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - qwen3
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - qwen3
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 12288,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "max_position_embeddings": 40960,
52
+ "max_window_layers": 36,
53
+ "model_type": "qwen3",
54
+ "num_attention_heads": 32,
55
+ "num_hidden_layers": 36,
56
+ "num_key_value_heads": 8,
57
+ "pad_token_id": 151654,
58
+ "quantization_config": {
59
+ "bnb_4bit_compute_dtype": "bfloat16",
60
+ "bnb_4bit_quant_type": "nf4",
61
+ "bnb_4bit_use_double_quant": true,
62
+ "llm_int8_enable_fp32_cpu_offload": false,
63
+ "llm_int8_has_fp16_weight": false,
64
+ "llm_int8_skip_modules": null,
65
+ "llm_int8_threshold": 6.0,
66
+ "load_in_4bit": true,
67
+ "load_in_8bit": false,
68
+ "quant_method": "bitsandbytes"
69
+ },
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_scaling": null,
72
+ "rope_theta": 1000000,
73
+ "sliding_window": null,
74
+ "tie_word_embeddings": false,
75
+ "torch_dtype": "bfloat16",
76
+ "transformers_version": "4.53.1",
77
+ "unsloth_fixed": true,
78
+ "unsloth_version": "2025.7.3",
79
+ "use_cache": true,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 40960,
9
+ "pad_token_id": 151654,
10
+ "temperature": 0.6,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.53.1"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0179e42bfe92c2f8b8a5c4f18435f2c0cb0ee94a8bdbbe36180e1d7abb9e338e
3
+ size 4975369208
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29c12a301c26fd623259ff294cffc26574fb9fcd73b526ea6b3b5cbb37a03f3
3
+ size 2504973822
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff