Downloads · 30 days
10
34% of all-time downloads
qwen3-4b-tau2-telecom_u1_sample74-1ep
MANGSEOK123/qwen3-4b-tau2-telecom_u1_sample74-1ep
qwen3-4b-tau2-telecom_u1_sample74-1ep is a machine learning model from MANGSEOK123. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3-4B-Instruct-2507 consolidated with OEL on the tau2-bench telecom domain, using 72 task–memory pairs.
All-time downloads
29
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- 8361a703
Base models
Model card
From the Hugging Face model README
Qwen3-4B-Instruct-2507 — tau2-bench telecom
Qwen3-4B-Instruct-2507 consolidated with OEL on the tau2-bench telecom domain, using 72 task–memory pairs.
Training
| base model | Qwen3-4B-Instruct-2507 |
| training pairs | 72 |
| batch size | 6 |
| epochs | 1 |
| learning rate | 3e-6, constant |
| gradient clipping | 1.0 (verl default) |
| loss | full KL over all response tokens, kl_topk 256 |
| user simulator | gpt-4.1-mini (temperature 0) |
The student replays each task without memory; the teacher is the same weights with that task's memory in the system prompt. Only the prompt differs, and no reward is used.
| step | KL loss | entropy | grad norm |
|---|---|---|---|
| 1 | 0.016 | 0.230 | 5.296 |
| 2 | 0.012 | 0.415 | 1.243 |
| 3 | 0.007 | 0.122 | 1.300 |
| 4 | 0.012 | 0.492 | 5.999 |
| 5 | 0.013 | 0.405 | 1.237 |
| 6 | 0.011 | 0.272 | 1.157 |
| 7 | 0.018 | 0.204 | 2.431 |
| 8 | 0.013 | 0.487 | 1.068 |
| 9 | 0.036 | 0.219 | 2.306 |
| 10 | 0.096 | 0.170 | 18.221 |
| 11 | 0.018 | 0.411 | 1.259 |
| 12 | 0.014 | 0.488 | 1.204 |
Each step reads a different batch, so the loss column tracks batch difficulty rather than convergence.
Evaluation
Not evaluated. Pushed straight after training. For reference the base model scores
avg 0.056 / pass@4 0.175 on the tau2-bench telecom test split.
Usage
vllm serve MANGSEOK123/qwen3-4b-tau2-telecom_u1_sample74-1ep \
--enable-auto-tool-choice --tool-call-parser hermes --max-model-len 40960
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026