ainewtrend07 commited on
Commit
ce8bf7f
·
verified ·
1 Parent(s): c28a856

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show
  1. config.json +74 -0
  2. generation_config.json +14 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
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
+ ],
43
+ "max_position_embeddings": 40960,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen3",
46
+ "num_attention_heads": 16,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 8,
49
+ "pad_token_id": 151654,
50
+ "quantization_config": {
51
+ "bnb_4bit_compute_dtype": "float16",
52
+ "bnb_4bit_quant_type": "nf4",
53
+ "bnb_4bit_use_double_quant": true,
54
+ "llm_int8_enable_fp32_cpu_offload": false,
55
+ "llm_int8_has_fp16_weight": false,
56
+ "llm_int8_skip_modules": null,
57
+ "llm_int8_threshold": 6.0,
58
+ "load_in_4bit": true,
59
+ "load_in_8bit": false,
60
+ "quant_method": "bitsandbytes"
61
+ },
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000,
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": true,
67
+ "torch_dtype": "float16",
68
+ "transformers_version": "4.55.4",
69
+ "unsloth_fixed": true,
70
+ "unsloth_version": "2025.10.1",
71
+ "use_cache": true,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
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": "4.55.4"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004d29fbf671645c3c9553b3b0c9bb3abbce6362e1f8f7d539230c8c62c534d0
3
+ size 1198544944