infly/OpenCoder-8B-Instruct

Full fine-tune vs infly/OpenCoder-8B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 1/1

5 derivatives checked

• bartowski/OpenCoder-8B-Instruct-GGUF: Same weights, converted
• mradermacher/OpenCoder-8B-Instruct-i1-GGUF: Quantization
• mradermacher/OpenCoder-8B-Instruct-GGUF: Same weights, converted
• lmstudio-community/OpenCoder-8B-Instruct-GGUF: Quantization
• DevQuasar-5/infly.OpenCoder-8B-Instruct-GGUF: Quantization

On the Hub · Downloads on Model Pulse