johnsnowlabs/JSL-MedLlama-3-8B-v1.0
Full fine-tune vs meta-llama/Meta-Llama-3-8B. 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
6 derivatives checked
- shanchen/llama3-8B-slerp-med-chinese: LoRA-style
- featherless-ai-quants/johnsnowlabs-JSL-MedLlama-3-8B-v1.0-GGUF: Quantization
- mradermacher/JSL-MedLlama-3-8B-v1.0-GGUF: Same weights, converted
- tensorblock/JSL-MedLlama-3-8B-v1.0-GGUF: Quantization
- arcee-ai/Llama-3-Medical-JSL-WiNGPT2-SLERP: LoRA-style
- 007ankit/JSL-MedLlama-3-8B-v1.0-Llama-3-8B-Hindi-Sathi-v0.1: Full fine-tune