ByteDance-Seed/Seed-Coder-8B-Reasoning
Full fine-tune vs ByteDance-Seed/Seed-Coder-8B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- unsloth/Seed-Coder-8B-Reasoning-GGUF: Partial fine-tune
- mradermacher/Seed-Coder-8B-Reasoning-i1-GGUF: Quantization
- second-state/Seed-Coder-8B-Reasoning-GGUF: Same weights, converted
- mradermacher/Seed-Coder-8B-Reasoning-GGUF: Same weights, converted
- gaianet/Seed-Coder-8B-Reasoning-GGUF: Same weights, converted
- DevQuasar/ByteDance-Seed.Seed-Coder-8B-Reasoning-GGUF: Same weights, converted
- jkim96/Seed-Coder-8B-Reasoning-DASHQ-Q2-GGUF: Quantization
- yongqiqng/AutoBM-Seed-Coder-8B-R: Full fine-tune