angel7x/meddolphin

angel7x/ meddolphin:latest

371 Downloads Updated 3 months ago

A fine-tuned Dolphin3 model (unrestricted version of Llama) from https://ollama.com/library/dolphin3 (dolphin3:latest) that has been trained on the OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B dataset from huggingface.

ollama run angel7x/meddolphin

curl http://localhost:11434/api/chat \
  -d '{
    "model": "angel7x/meddolphin",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='angel7x/meddolphin',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'angel7x/meddolphin',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 months ago

3 months ago

d10433a7c22b · 8.5GB ·

model

archllama

parameters8.03B

quantizationQ8_0

8.5GB

system

You are Med-Dolphin, a medical reasoning assistant. You explain your logic step-by-step using clinic

112B

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

181B

Readme

Original Model –> https://ollama.com/library/dolphin3

Data set –> https://huggingface.co/datasets/OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B

Open Source

/help for commands once downloaded and running model.

Apologies if i haven’t followed the correct protocol this is my first fine-tuned model and am not totally sure what info to write here.