Open-weight model
gemma-3-4b-it-tree_willow-STEER1.5-ft4.42
by Yanan He Echoo113/gemma-3-4b-it-tree_willow-STEER1.5-ft4.42
gemma-3-4b-it-tree_willow-STEER1.5-ft4.42 is an open-weight model from Yanan He. Its published files total 104.9 MB.
This model is a fine-tuned version of google/gemma-3-4b-it. It has been trained using TRL. This model was trained with SFT.
Model Card
This model is a fine-tuned version of google/gemma-3-4b-it. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Yanan He.
Identity and Version
- Repository
- Echoo113/gemma-3-4b-it-tree_willow-STEER1.5-ft4.42
- Publisher
- Yanan He
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- sft, trl
- Revision
- 78a40b84f8f712327a3a341985f9771673c4beb7
- First published
- 2026-10-17
- Last updated
- 2026-10-17
Files and Weights
11 files, 104.9 MB in total. The weights are 2 files totalling 65.7 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 65.7 MB | 6b22610f759b |
| training_args.bin | Weights | 6.5 KB | 14a91e6e895b |
| adapter_config.json | Configuration | 901 B | — |
| added_tokens.json | Configuration | 35 B | — |
| special_tokens_map.json | Configuration | 662 B | — |
| README.md | Documentation | 1.5 KB | — |
| chat_template.jinja | Other | 1.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 33.4 MB | 4667f2089529 |
| tokenizer.model | Tokenizer | 4.7 MB | 1299c11d7cf6 |
| tokenizer_config.json | Tokenizer | 1.2 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 65.7 MB
Released by Yanan He through its official repository on Hugging Face.
Built From
- Derived from google/gemma-3-4b-it
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 65.7 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.