PokeeAI/pokee_research_7b

Partial fine-tune vs Qwen/Qwen2.5-7B-Instruct. Partial change: 84% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 46/57, MLP 82/84, Attention 188/196, lm_head 0/1

2 derivatives checked

• bartowski/PokeeAI_pokee_research_7b-GGUF: Same weights, converted
• DevQuasar/PokeeAI.pokee_research_7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse