AF0815 commited on
Commit
bdf7c69
·
verified ·
1 Parent(s): 8475b6d

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

Browse files
README.md CHANGED
@@ -17,6 +17,7 @@ tags:
17
  - agentbench
18
  - alfworld
19
  - dbbench
 
20
  ---
21
 
22
  # qwen3-4b-agentbench-dbalf-lora
@@ -48,12 +49,12 @@ Loss is applied to **all assistant turns** in the trajectory, enabling the model
48
  - Mixing ratio (pre-merge target): **DB:ALF = 1:0**
49
 
50
  ### DB Oversampling (category-aware)
51
- Enabled: **False**
52
 
53
  DB category weights used during training-data preparation:
54
 
55
  - counting: 2
56
- - comparison: 2
57
  - ranking: 1
58
  - select: 1
59
  - insert: 1
 
17
  - agentbench
18
  - alfworld
19
  - dbbench
20
+ - db-oversampling
21
  ---
22
 
23
  # qwen3-4b-agentbench-dbalf-lora
 
49
  - Mixing ratio (pre-merge target): **DB:ALF = 1:0**
50
 
51
  ### DB Oversampling (category-aware)
52
+ Enabled: **True**
53
 
54
  DB category weights used during training-data preparation:
55
 
56
  - counting: 2
57
+ - comparison: 1
58
  - ranking: 1
59
  - select: 1
60
  - insert: 1
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0904653db93ddb70ebf902f1ac94e654ea3edaed528643fff0f0baad8319f7
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9583b85b53dfc82008b452debc3e07462a46b8910ed0a96feb940bf763365a
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:d5a07af9afe93e9a832881b22b648f88e41b9c91a641ca512cbf38ad5da112f0
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc57f0db9cec8c8721aa56c73ea24b7b110b549645c345745f934d1b059aaba
3
  size 3077766632