Downloads · 30 days
10
3% of all-time downloads
lihaoxin2020/qwen3.5-4B-evidence-subagent-gpt54-single-jina-v2-no-urls-64k-no-exact-cutoff-full-sft-v1-lr2e-5
qwen3.5-4B-evidence-subagent-gpt54-single-jina-v2-no-urls-64k-no-exact-cutoff-full-sft-v1-lr2e-5 is a image-text-to-text model from lihaoxin2020. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
3% of all-time downloads
All-time downloads
333
Public
Parameters
5.2B
10.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors10.4 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Qwen/Qwen3.5-4B on the evidence_subagent_sft_gpt54_single_all_jina_v2_aligned_no_urls_64k_no_exact_cutoff dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6192 | 0.1554 | 100 | 0.6542 |
| 0.5349 | 0.3108 | 200 | 0.6279 |
| 0.6548 | 0.4662 | 300 | 0.6240 |
| 0.5665 | 0.6216 | 400 | 0.6094 |
| 0.6513 | 0.7770 | 500 | 0.5980 |
| 0.6115 | 0.9324 | 600 | 0.5876 |
| 0.2951 | 1.0870 | 700 | 0.6275 |
| 0.2840 | 1.2424 | 800 | 0.6213 |
| 0.3220 | 1.3978 | 900 | 0.6083 |
| 0.3101 | 1.5532 | 1000 | 0.6067 |
| 0.2567 | 1.7086 | 1100 | 0.6037 |
| 0.2680 | 1.8640 | 1200 | 0.6004 |