da1ch812 commited on
Commit
4d8decf
·
verified ·
1 Parent(s): 9229f5d

Upload merged unsloth/Qwen3-4B-Instruct-2507 model (auto-generated README)

Browse files
README.md CHANGED
@@ -1,7 +1,10 @@
1
  ---
2
  base_model: unsloth/Qwen3-4B-Instruct-2507
3
  datasets:
 
4
  - u-10bei/dbbench_sft_dataset_react
 
 
5
  language:
6
  - en
7
  license: apache-2.0
@@ -33,8 +36,8 @@ tool use, and recovery from errors.
33
 
34
  - Base model: unsloth/Qwen3-4B-Instruct-2507
35
  - Method: LoRA
36
- - dtype: torch.bfloat16
37
- - load_in_4bit: False
38
  - Max sequence length: 2048
39
  - Epochs: 2
40
  - Learning rate: 2e-06
@@ -58,8 +61,12 @@ model = AutoModelForCausalLM.from_pretrained(
58
 
59
  ## Sources & Terms (IMPORTANT)
60
 
61
- Training data:
 
62
  - u-10bei/dbbench_sft_dataset_react
 
 
63
 
64
  Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
65
- Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
 
 
1
  ---
2
  base_model: unsloth/Qwen3-4B-Instruct-2507
3
  datasets:
4
+ - u-10bei/dbbench_sft_dataset_react_v3
5
  - u-10bei/dbbench_sft_dataset_react
6
+ - u-10bei/dbbench_sft_dataset_react_v4
7
+ - u-10bei/dbbench_sft_dataset_react_v2
8
  language:
9
  - en
10
  license: apache-2.0
 
36
 
37
  - Base model: unsloth/Qwen3-4B-Instruct-2507
38
  - Method: LoRA
39
+ - dtype: torch.float16
40
+ - load_in_4bit: True
41
  - Max sequence length: 2048
42
  - Epochs: 2
43
  - Learning rate: 2e-06
 
61
 
62
  ## Sources & Terms (IMPORTANT)
63
 
64
+ Training data:
65
+ - u-10bei/dbbench_sft_dataset_react_v3
66
  - u-10bei/dbbench_sft_dataset_react
67
+ - u-10bei/dbbench_sft_dataset_react_v4
68
+ - u-10bei/dbbench_sft_dataset_react_v2
69
 
70
  Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
71
+ Compliance: Users must comply with the MIT license (including copyright notice)
72
+ and the base model's original terms of use.
config.json CHANGED
@@ -4,7 +4,7 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "dtype": "bfloat16",
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
 
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "dtype": "float16",
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b548ca350ccfd7e6b50af77cd5cb296374c029cb94acba85cae8854fa357735f
3
- size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a375c96358c3374d4f22c17492e241481055e4a403862e7a09dba1aa8c81f51f
3
+ size 4967215128
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c06842070760200934a1818592a41c844bb6b9d8455328c7a3c395b4a6398b59
3
- size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4b4e10e017af901e896c4e8b6f7635abd48d74712b216b5d722afe0cbf5782
3
+ size 3077766464