Hugging Face's logo

wan-wan
/
test05

Text Generation
PEFT
Safetensors
English
qwen3
lora
agent
tool-use
alfworld
dbbench
conversational
Model card Files
xet
Community
wan-wan commited on
Commit
55d6c5d
·
verified ·
1 Parent(s): 772f2b3

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

Browse files
Files changed (3) hide show
  1. README.md +3 -3
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -36,9 +36,9 @@ tool use, and recovery from errors.
36
 
37
  - Base model: Qwen/Qwen3-4B-Instruct-2507
38
  - Method: LoRA (full precision base)
39
- - Max sequence length: 2048
40
- - Epochs: 1
41
- - Learning rate: 5e-06
42
  - LoRA: r=64, alpha=128
43
 
44
  ## Usage
 
36
 
37
  - Base model: Qwen/Qwen3-4B-Instruct-2507
38
  - Method: LoRA (full precision base)
39
+ - Max sequence length: 512
40
+ - Epochs: 2
41
+ - Learning rate: 2e-06
42
  - LoRA: r=64, alpha=128
43
 
44
  ## Usage
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36d3515067dbed6ab5be03686b06141e1d4ada1591a006b83e1160e4c735e534
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e952dc44a7d98a4cfba0ad7461de3fea4cfaa969d82bcf4ded38223972130e29
3
  size 4967215360
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0858acd4edd5b488538560e2b3731a74ac980aaad79c22321666664f3f2eb11b
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28f3e8a5d7fb5af655bcb3355fd8636433b94371043f03017142a9eb0dd5c9c
3
  size 3077766632