Upload merged unsloth/Qwen3-4B-Instruct-2507 model (auto-generated README)
Browse files- README.md +18 -4
- config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
README.md
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/Qwen3-4B-Instruct-2507
|
| 3 |
datasets:
|
| 4 |
-
- u-10bei/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
license: apache-2.0
|
|
@@ -33,8 +40,8 @@ tool use, and recovery from errors.
|
|
| 33 |
|
| 34 |
- Base model: unsloth/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: LoRA
|
| 36 |
-
- dtype: torch.
|
| 37 |
-
- load_in_4bit:
|
| 38 |
- Max sequence length: 2048
|
| 39 |
- Epochs: 2
|
| 40 |
- Learning rate: 2e-06
|
|
@@ -59,7 +66,14 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 59 |
## Sources & Terms (IMPORTANT)
|
| 60 |
|
| 61 |
Training data:
|
| 62 |
-
- u-10bei/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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)
|
|
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/Qwen3-4B-Instruct-2507
|
| 3 |
datasets:
|
| 4 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v2
|
| 5 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v3
|
| 6 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v4
|
| 7 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v5
|
| 8 |
+
- u-10bei/dbbench_sft_dataset_react
|
| 9 |
+
- u-10bei/dbbench_sft_dataset_react_v2
|
| 10 |
+
- u-10bei/dbbench_sft_dataset_react_v3
|
| 11 |
+
- u-10bei/dbbench_sft_dataset_react_v4
|
| 12 |
language:
|
| 13 |
- en
|
| 14 |
license: apache-2.0
|
|
|
|
| 40 |
|
| 41 |
- Base model: unsloth/Qwen3-4B-Instruct-2507
|
| 42 |
- Method: LoRA
|
| 43 |
+
- dtype: torch.bfloat16
|
| 44 |
+
- load_in_4bit: False
|
| 45 |
- Max sequence length: 2048
|
| 46 |
- Epochs: 2
|
| 47 |
- Learning rate: 2e-06
|
|
|
|
| 66 |
## Sources & Terms (IMPORTANT)
|
| 67 |
|
| 68 |
Training data:
|
| 69 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v2
|
| 70 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v3
|
| 71 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v4
|
| 72 |
+
- u-10bei/sft_alfworld_trajectory_dataset_v5
|
| 73 |
+
- u-10bei/dbbench_sft_dataset_react
|
| 74 |
+
- u-10bei/dbbench_sft_dataset_react_v2
|
| 75 |
+
- u-10bei/dbbench_sft_dataset_react_v3
|
| 76 |
+
- u-10bei/dbbench_sft_dataset_react_v4
|
| 77 |
|
| 78 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 79 |
Compliance: Users must comply with the MIT license (including copyright notice)
|
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"dtype": "
|
| 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": "bfloat16",
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b548ca350ccfd7e6b50af77cd5cb296374c029cb94acba85cae8854fa357735f
|
| 3 |
+
size 4967215360
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c06842070760200934a1818592a41c844bb6b9d8455328c7a3c395b4a6398b59
|
| 3 |
+
size 3077766632
|