NeuralNovel/Panda-7B-v0.1

Full fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• TheBloke/Panda-7B-v0.1-GGUF: Quantization
• mradermacher/Panda-7B-v0.1-i1-GGUF: Quantization
• mradermacher/Panda-7B-v0.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse