Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)
Browse files- README.md +2 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
|
@@ -15,7 +15,7 @@ tags:
|
|
| 15 |
- dbbench
|
| 16 |
---
|
| 17 |
|
| 18 |
-
# No.
|
| 19 |
|
| 20 |
This repository provides a **LoRA adapter** fine-tuned from
|
| 21 |
**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
|
|
@@ -37,7 +37,7 @@ tool use, and recovery from errors.
|
|
| 37 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 38 |
- Method: LoRA (full precision base)
|
| 39 |
- Max sequence length: 4096
|
| 40 |
-
- Epochs:
|
| 41 |
- Learning rate: 5e-06
|
| 42 |
- LoRA: r=64, alpha=64
|
| 43 |
|
|
|
|
| 15 |
- dbbench
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# No.18 advanced competition qwen3-4b-agent-trajectory-lora LR=4.5e-6 epoc=3 A100
|
| 19 |
|
| 20 |
This repository provides a **LoRA adapter** fine-tuned from
|
| 21 |
**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
|
|
|
|
| 37 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 38 |
- Method: LoRA (full precision base)
|
| 39 |
- Max sequence length: 4096
|
| 40 |
+
- Epochs: 3
|
| 41 |
- Learning rate: 5e-06
|
| 42 |
- LoRA: r=64, alpha=64
|
| 43 |
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4967215360
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de267111d360fe76d6efe41260f228bf96ac9b667ac1215f1214599e1795fc22
|
| 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 3077766632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685c368e46bb16c3036990464793409db5f52475510f1b36f46d900ca9570ce0
|
| 3 |
size 3077766632
|