NeuralNovel/Tiger-7B-v0.1

Full fine-tune vs NeuralNovel/Gecko-7B-v0.1-DPO. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 93/96, Embeddings 1/1, Norms 13/65, Attention 124/128, lm_head 1/1

2 derivatives checked

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

On the Hub · Downloads on Model Pulse