tokyotech-llm/GPT-OSS-Swallow-20B-RL-v0.1
Full fine-tune vs tokyotech-llm/GPT-OSS-Swallow-20B-SFT-v0.1. Fine-tune: 97% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 0/1, Norms 1/49, MLP 126/144, Attention 194/216, lm_head 1/1
11 derivatives checked
- mradermacher/GPT-OSS-Swallow-20B-RL-v0.1-i1-GGUF: Quantization
- mmnga-o/GPT-OSS-Swallow-20B-RL-v0.1-gguf: Quantization
- mradermacher/GPT-OSS-Swallow-20B-RL-v0.1-GGUF: Quantization
- tokyotech-llm/GPT-OSS-Swallow-20B-RL-v0.1-MXFP4: LoRA-style
- keitokei1994/GPT-OSS-Swallow-20B-RL-v0.1-GGUF: Quantization
- tokimoa/GPT-OSS-Swallow-20B-RL-v0.1-MLX-MXFP4: Quantization
- tocchitocchi/GPT-OSS-Swallow-20B-RL-v0.1-6bit-mlx: Quantization
- nobikko/GPT-OSS-Swallow-20B-RL-v0.1-GGUF: Quantization
- dahara1/GPT-OSS-Swallow-20B-RL-v0.1-MXFP4: Quantization
- tatsuyaaaaaaa/GPT-OSS-Swallow-20B-RL-v0.1-gguf: Same weights, converted
- yuseiito/GPT-OSS-Swallow-20B-RL-v0.1-GGUF: Same weights, converted