chip-0.8b is an open-weight model from Wenhua Huo. Its published files total 65.4 MB.
Chip is the main NL2Hull ship-design decision model. It adapts a Kev-style typed decision interface to Chinese natural-language ship-form editing requests and predicts probability distributions over ordered editing decisions.
Model Card
Chip is the main NL2Hull ship-design decision model. It adapts a Kev-style typed decision interface to Chinese natural-language ship-form editing requests and predicts probability distributions over ordered editing decisions. This release contains the LoRA adapter and the learned decision head for the 0.8-billion-parameter Chip model. The adapter is applied to Qwen/Qwen3.5-0.8B-Base; the head.pt file is required by the NL2Hull/Kev inference implementation. - adaptermodel.safetensors: LoRA adapter weights - adapterconfig.json: PEFT adapter configuration - head.pt: learned typed-decision head - tokenizer.json, tokenizerconfig.json, chattemplate.jinja: tokenizer files - trainingconfig.json…
Excerpt from the card by Wenhua Huo.
Identity and Version
- Repository
- wenhuahuo/chip-0.8b
- Publisher
- Wenhua Huo
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- e5213f342331e91ef6f8eb052fa610fc6b17937e
- First published
- 2026-10-07
- Last updated
- 2026-10-08
Files and Weights
10 files, 65.4 MB in total. The weights are 2 files totalling 45.4 MB in pt, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 43.3 MB | 72f7e80900e9 |
| head.pt | Weights | 2.1 MB | 5098aeac17ce |
| adapter_config.json | Configuration | 1.3 KB | — |
| training_config.json | Configuration | 2.0 KB | — |
| training_metrics.json | Configuration | 327 B | — |
| README.md | Documentation | 3.2 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 45.4 MB
Released by Wenhua Huo through its official repository on Hugging Face.
Built From
- Adapter of Qwen/Qwen3.5-0.8B-Base
- Derived from Qwen/Qwen3.5-0.8B-Base
- Described by arXiv:2610.09896
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 45.4 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.