SakanaAI/TinySwallow-1.5B-Instruct
Full fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
15 derivatives checked
- bartowski/TinySwallow-1.5B-Instruct-GGUF: Same weights, converted
- mradermacher/TinySwallow-1.5B-Instruct-i1-GGUF: Quantization
- featherless-ai-quants/SakanaAI-TinySwallow-1.5B-Instruct-GGUF: Quantization
- mmnga/TinySwallow-1.5B-Instruct-gguf: Quantization
- tatsuyaaaaaaa/TinySwallow-1.5B-Instruct-gguf: Quantization
- mradermacher/TinySwallow-1.5B-Instruct-GGUF: Same weights, converted
- ysn-rfd/TinySwallow-1.5B-Instruct-GGUF: Quantization
- DevQuasar-3/SakanaAI.TinySwallow-1.5B-Instruct-GGUF: Same weights, converted
- oriental-lab/Tr-Jp-LLM-1.5B: Full fine-tune
- Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp: Full fine-tune
- EQUES/OpenRS3-GRPO-ja: Full fine-tune
- oriental-lab/Tr-Jp-LLM-1.5B-v2: Partial fine-tune
- oriental-lab/TinySwallow-1.5B-dolly_tl: Full fine-tune
- EQUES/TinySwallow-Stratos-1.5B: Full fine-tune
- Atotti/TinySwallow-GRPO-TakahashiMethod-v0.2: LoRA-style