allenai/llama-3.1-tulu-2-8b

Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

3 derivatives checked

• mradermacher/llama-3.1-tulu-2-8b-i1-GGUF: Quantization
• mradermacher/llama-3.1-tulu-2-8b-GGUF: Same weights, converted
• allenai/llama-3.1-tulu-2-dpo-8b: Full fine-tune

On the Hub · Downloads on Model Pulse