---
language: en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- ruslanmv
- llama
- trl
- llama-3
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- distillation
- heathcare
- medical
- clinical
- med
- lifescience
- Pharmaceutical
- Pharma
- TensorBlock
- GGUF
base_model: ruslanmv/Medical-Llama3-8B
datasets:
- ruslanmv/ai-medical-chatbot
widget:
- example_title: Medical-Llama3-8B
  messages:
  - role: system
    content: You are an expert and experienced from the healthcare and biomedical
      domain with extensive medical knowledge and practical experience.
  - role: user
    content: How long does it take for newborn jaundice to go away?
  output:
    text: Newborn jaundice, also known as neonatal jaundice, is a common condition
      in newborns where the yellowing of the skin and eyes occurs due to an elevated
      level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when
      red blood cells break down. In most cases, newborn jaundice resolves on its
      own without any specific treatment. The duration of newborn jaundice can vary
      depending on several factors such as the underlying cause, gestational age at
      birth, and individual variations in bilirubin metabolism. Here are some general
      guidelines
model-index:
- name: Medical-Llama3-8B
  results: []
---

<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;">
            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
        </p>
    </div>
</div>

## ruslanmv/Medical-Llama3-8B - GGUF

This repo contains GGUF format model files for [ruslanmv/Medical-Llama3-8B](https://huggingface.co/ruslanmv/Medical-Llama3-8B).

The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).


<div style="text-align: left; margin: 20px 0;">
    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
        Run them on the TensorBlock client using your local machine ↗
    </a>
</div>

## Prompt template


```

```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Medical-Llama3-8B-Q2_K.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
| [Medical-Llama3-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
| [Medical-Llama3-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
| [Medical-Llama3-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
| [Medical-Llama3-8B-Q4_0.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Medical-Llama3-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
| [Medical-Llama3-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
| [Medical-Llama3-8B-Q5_0.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Medical-Llama3-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
| [Medical-Llama3-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
| [Medical-Llama3-8B-Q6_K.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
| [Medical-Llama3-8B-Q8_0.gguf](https://huggingface.co/tensorblock/Medical-Llama3-8B-GGUF/blob/main/Medical-Llama3-8B-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |


## Downloading instruction

### Command line

Firstly, install Huggingface Client

```shell
pip install -U "huggingface_hub[cli]"
```

Then, downoad the individual model file the a local directory

```shell
huggingface-cli download tensorblock/Medical-Llama3-8B-GGUF --include "Medical-Llama3-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```

If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:

```shell
huggingface-cli download tensorblock/Medical-Llama3-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```