OpenBuddy/openbuddy-qwen2.5coder-32b-v24.1q-200k

Full fine-tune vs Qwen/Qwen2.5-Coder-32B-Instruct. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• bartowski/openbuddy-qwen2.5coder-32b-v24.1q-200k-GGUF: Same weights, converted
• mradermacher/openbuddy-qwen2.5coder-32b-v24.1q-200k-i1-GGUF: Quantization
• mradermacher/openbuddy-qwen2.5coder-32b-v24.1q-200k-GGUF: Quantization

On the Hub · Downloads on Model Pulse