retrieva-jp/Llama-3-Swallow-8B-Instruct-v0.1-kokoroe

Full fine-tune vs tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1. Fine-tune: 93% 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

2 derivatives checked

• mradermacher/Llama-3-Swallow-8B-Instruct-v0.1-kokoroe-i1-GGUF: Quantization
• mradermacher/Llama-3-Swallow-8B-Instruct-v0.1-kokoroe-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse