BlossomsAI/BloomVN-8B-chat

Full fine-tune vs sail/Sailor2-8B-Chat. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/224, lm_head 1/1

2 derivatives checked

• mradermacher/BloomVN-8B-chat-GGUF: Same weights, converted
• BlossomsAI/BloomVN-8B-Chat-Reasoning: LoRA-style

On the Hub · Downloads on Model Pulse