Instructions to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Ollama
How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with Ollama:
```
ollama run hf.co/afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF to start chatting

Docker Model Runner
How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.dolphin-2.9.3-qwen2-0.5b-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

dolphin-2.9.3-qwen2-0.5b-GGUF

Quantized GGUF model files for dolphin-2.9.3-qwen2-0.5b from cognitivecomputations

Original Model Card:

Dolphin 2.9.3 Qwen2 0.5B 🐬

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsors of Dolphin 2.9.3:

Crusoe Cloud - provided excellent on-demand 8xH100 node

This model is based on Qwen2-0.5b, and is governed by the Apache-2.0

The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.

Due to the complexities of fine tuning smaller models on datasets created by/for larger models - we removed coding, function calling and systemchat-multilingual datasets when tuning these models.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Dolphin-2.9.3 has a variety of instruction, and conversational skills.

Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Dolphin is licensed according to Apache-2.0 We grant permission for any use, including commercial, that falls within accordance with said license. Dolphin was trained on data generated from GPT4, among other models.

Evals:

Downloads last month: 222

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF

Base model

Qwen/Qwen2-0.5B

Finetuned

dphn/dolphin-2.9.3-qwen2-0.5b

Quantized

(4)

this model

afrideva
/

dolphin-2.9.3-qwen2-0.5b-GGUF

dolphin-2.9.3-qwen2-0.5b-GGUF

Original Model Card:

Dolphin 2.9.3 Qwen2 0.5B 🐬

Model tree for afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF

Datasets used to train afrideva/dolphin-2.9.3-qwen2-0.5b-GGUF