Open-weight model
qwen3-vl-8b-hebrew-v22b-ckpt
by Isaac Godfried isaacmg/qwen3-vl-8b-hebrew-v22b-ckpt
qwen3-vl-8b-hebrew-v22b-ckpt is an open-weight model from Isaac Godfried. Its published files total 550.0 MB.
This model is a fine-tuned version of unsloth/qwen3-vl-8b-instruct-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with SFT.
Model Card
This model is a fine-tuned version of unsloth/qwen3-vl-8b-instruct-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Isaac Godfried.
Identity and Version
- Repository
- isaacmg/qwen3-vl-8b-hebrew-v22b-ckpt
- Publisher
- Isaac Godfried
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- trl, sft
- Revision
- ae73ae7a72baaa6ada4e98aeb5834a2d8432fd88
- First published
- 2026-10-02
- Last updated
- 2026-10-05
Files and Weights
32 files, 550.0 MB in total. The weights are 7 files totalling 518.0 MB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 205.5 MB | 849511c70bef |
| last-checkpoint/adapter_model.safetensors | Weights | 205.5 MB | 849511c70bef |
| last-checkpoint/optimizer.pt | Weights | 107.0 MB | 3e6fb0a072bf |
| last-checkpoint/rng_state.pth | Weights | 14.6 KB | ea074dd1404e |
| last-checkpoint/scheduler.pt | Weights | 1.5 KB | 97a1ac5e05ab |
| last-checkpoint/training_args.bin | Weights | 6.4 KB | 1c62ea6ade3a |
| training_args.bin | Weights | 6.4 KB | 1c62ea6ade3a |
| adapter_config.json | Configuration | 1.7 KB | — |
| added_tokens.json | Configuration | 707 B | — |
| last-checkpoint/adapter_config.json | Configuration | 1.7 KB | — |
| last-checkpoint/added_tokens.json | Configuration | 707 B | — |
| last-checkpoint/preprocessor_config.json | Configuration | 788 B | — |
| last-checkpoint/special_tokens_map.json | Configuration | 614 B | — |
| last-checkpoint/trainer_state.json | Configuration | 26.3 KB | — |
| last-checkpoint/video_preprocessor_config.json | Configuration | 817 B | — |
| preprocessor_config.json | Configuration | 788 B | — |
| session_plan.json | Configuration | 129.5 KB | — |
| special_tokens_map.json | Configuration | 614 B | — |
| video_preprocessor_config.json | Configuration | 817 B | — |
| README.md | Documentation | 1.8 KB | — |
| last-checkpoint/README.md | Documentation | 5.3 KB | — |
| chat_template.jinja | Other | 5.3 KB | — |
| last-checkpoint/chat_template.jinja | Other | 5.3 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| last-checkpoint/merges.txt | Tokenizer | 1.7 MB | — |
| last-checkpoint/tokenizer.json | Tokenizer | 11.4 MB | c0815702d207 |
| last-checkpoint/tokenizer_config.json | Tokenizer | 5.5 KB | — |
| last-checkpoint/vocab.json | Tokenizer | 2.8 MB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | c0815702d207 |
| tokenizer_config.json | Tokenizer | 5.5 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 518.0 MB
Released by Isaac Godfried through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 518.0 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.