ByteDance-Seed/Seed-Coder-8B-Instruct
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
10 derivatives checked
- unsloth/Seed-Coder-8B-Instruct-GGUF: Same weights, converted
- mradermacher/Seed-Coder-8B-Instruct-i1-GGUF: Quantization
- snsnc/Seed-Coder-8B-Instruct-Rust-Strandset-GGUF: Full fine-tune
- mradermacher/Seed-Coder-8B-Instruct-GGUF: Same weights, converted
- second-state/Seed-Coder-8B-Instruct-GGUF: Same weights, converted
- gaianet/Seed-Coder-8B-Instruct-GGUF: Same weights, converted
- DevQuasar/ByteDance-Seed.Seed-Coder-8B-Instruct-GGUF: Same weights, converted
- unsloth/Seed-Coder-8B-Instruct-unsloth-bnb-4bit: Quantization
- jc-builds/Seed-Coder-8B-Instruct-GGUF: Quantization
- willyli/Seed-Coder-8B-Instruct-KTO: Full fine-tune
2 other repos hold byte-for-byte identical weight files.