Instructions to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF",
	filename="dolphin-2.9.2-phi-3-medium.q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-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 macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-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 macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M

Use Docker

docker model run hf.co/macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with Ollama:
```
ollama run hf.co/macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
```

Unsloth Studio

How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-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 macadeliccc/dolphin-2.9.2-Phi-3-Medium-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 macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF to start chatting

Docker Model Runner
How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with Docker Model Runner:
```
docker model run hf.co/macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M
```

Lemonade

How to use macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.dolphin-2.9.2-Phi-3-Medium-GGUF-Q4_K_M

List all available models

lemonade list

Original Model Card

Dolphin 2.9.2 Phi 3 Medium 🐬

Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsor of Dolphin 2.9.2:

Crusoe Cloud - provided excellent on-demand 8xL40Snode

This model is based on Phi-3-Medium-Instruct-4k, and is governed by the MIT license with which Microsoft released Phi-3.

Since Microsoft only released the fine-tuned model - Dolphin-2.9.2-Phi-3-Medium has not been entirely cleaned of refusals.

The base model has 4k context, and the qLoRA fine-tuning was with 4k sequence length.

It took 3.5 days on 8xL40S node provided by Crusoe Cloud

This model uses the ChatML prompt template.

example:

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

Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. 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. 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.

evals:

Downloads last month: 46

GGUF

Model size

14B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF

Base model

unsloth/Phi-3-mini-4k-instruct

Quantized

(19)

this model

macadeliccc
/

dolphin-2.9.2-Phi-3-Medium-GGUF

Dolphin 2.9.2 Phi 3 Medium 🐬

evals:

Model tree for macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF

Datasets used to train macadeliccc/dolphin-2.9.2-Phi-3-Medium-GGUF