rinnaNekomata
Nekomata 7B Instruction
This model instruction-tunes Nekomata 7B, retaining its Qwen ancestry and using the Alpaca task format.
Instruction data adds task-following behavior
The card lists Dolly, Japanese Dolly, FLAN and selected Izumi Lab bilingual datasets. The original Nekomata tokenizer is retained. Official GGUF files are packaging variants of this release.Nekomata 7B Instruction official model card
Compare instruction accuracy with the base
Practical guidance. Use a fixed set of short transformations to check whether instruction tuning improves the required behavior. Separate output-format compliance from factual accuracy.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | nekomata-7b-instructionnekomata-7b-instruction-gguf |
| License | Tongyi Qianwen License Agreement.Nekomata 7B Instruction official model card |
| Architecture | 32 layers with hidden width 4,096.Nekomata 7B Instruction official model card |
Related models
- Nekomata 14B Instruction
rinna · Nekomata
This model instruction-tunes Nekomata 14B, retaining its Qwen ancestry and using the Alpaca task format.
Launch date not confirmedDownloadable - Nekomata 7B
rinna · Nekomata
Nekomata 7B continues pretraining Qwen-7B on about 30B tokens of Japanese and English text.
Launch date not confirmedResearch releaseDownloadable