maldv/Awqward2.5-32B-Instruct

Full fine-tune vs AiCloser/Qwen2.5-32B-AGI. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 0/129, MLP 192/192, Attention 308/448, lm_head 0/1

3 derivatives checked

• mradermacher/Awqward2.5-32B-Instruct-i1-GGUF: Quantization
• featherless-ai-quants/maldv-Awqward2.5-32B-Instruct-GGUF: Quantization
• mradermacher/Awqward2.5-32B-Instruct-GGUF: Quantization

On the Hub · Downloads on Model Pulse