Base model: "YBXL/Med-LLaMA3-8B"
Developed by: RUI SHI
Dataset: "YBXL/train_chat_filtered"
Epoch(es): 0.5 (Commit id: 9b76d9f -> b1b5ae4) & 1.5 (Commit id: da0ca7e -> d0d5d01) & 2.0 (Commit id: c4d3079 -> 4381bb7)
License: apache-2.0

This llama model was trained by Huggingface's TRL library, using "YBXL/train_chat_filtered" diagnosis question and answering dataset.

Downloads last month: 28

Safetensors

Model size

8.03B params

Tensor type

BF16

Inference API

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for YBXL/Med-LLaMA3-8B-ft0.5

Base model

unsloth/llama-3-8b-Instruct-bnb-4bit

Finetuned

this model