Instructions to use jeremygracey-ai/FetchMerck_AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeremygracey-ai/FetchMerck_AI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jeremygracey-ai/FetchMerck_AI",
	filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

llama-cpp-python

How to use jeremygracey-ai/FetchMerck_AI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jeremygracey-ai/FetchMerck_AI",
	filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use jeremygracey-ai/FetchMerck_AI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jeremygracey-ai/FetchMerck_AI:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jeremygracey-ai/FetchMerck_AI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jeremygracey-ai/FetchMerck_AI:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jeremygracey-ai/FetchMerck_AI: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 jeremygracey-ai/FetchMerck_AI:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jeremygracey-ai/FetchMerck_AI: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 jeremygracey-ai/FetchMerck_AI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jeremygracey-ai/FetchMerck_AI:Q4_K_M

Use Docker

docker model run hf.co/jeremygracey-ai/FetchMerck_AI:Q4_K_M

LM Studio
Jan

vLLM

How to use jeremygracey-ai/FetchMerck_AI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeremygracey-ai/FetchMerck_AI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeremygracey-ai/FetchMerck_AI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jeremygracey-ai/FetchMerck_AI:Q4_K_M

Ollama
How to use jeremygracey-ai/FetchMerck_AI with Ollama:
```
ollama run hf.co/jeremygracey-ai/FetchMerck_AI:Q4_K_M
```

Unsloth Studio new

How to use jeremygracey-ai/FetchMerck_AI 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 jeremygracey-ai/FetchMerck_AI 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 jeremygracey-ai/FetchMerck_AI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jeremygracey-ai/FetchMerck_AI to start chatting

Docker Model Runner
How to use jeremygracey-ai/FetchMerck_AI with Docker Model Runner:
```
docker model run hf.co/jeremygracey-ai/FetchMerck_AI:Q4_K_M
```

Lemonade

How to use jeremygracey-ai/FetchMerck_AI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jeremygracey-ai/FetchMerck_AI:Q4_K_M

Run and chat with the model

lemonade run user.FetchMerck_AI-Q4_K_M

List all available models

lemonade list

FetchMerck_AI / Dockerfile

jeremygracey-ai

Initial upload of Dockerfile

9f10167 verified about 2 months ago

raw

history blame contribute delete

1.38 kB

	FROM python:3.12-slim

	# Install system dependencies for building llama-cpp-python
	RUN apt-get update && apt-get install -y \
	build-essential \
	python3-dev \
	cmake \
	&& rm -rf /var/lib/apt/lists/*

	# Set working directory
	WORKDIR /app

	# Install required Python libraries
	RUN pip install --no-cache-dir \
	fastapi \
	uvicorn \
	pydantic \
	huggingface_hub==0.35.3 \
	pandas==2.2.2 \
	tiktoken==0.12.0 \
	pymupdf==1.26.5 \
	langchain==0.3.27 \
	langchain-community==0.3.31 \
	chromadb==1.1.1 \
	sentence-transformers==5.1.1 \
	llama-cpp-python==0.2.28 \
	'numpy<2.1.0'

	# Copy the application logic and FastAPI server
	COPY app_logic.py main.py ./

	# Copy the persistent vector database directory
	COPY chroma_db/ ./chroma_db/

	# Create the directory structure for the model to match main.py's MODEL_PATH
	RUN mkdir -p /root/.cache/huggingface/hub/models--TheBloke--Mistral-7B-Instruct-v0.1-GGUF/snapshots/731a9fc8f06f5f5e2db8a0cf9d256197eb6e05d1/

	# Copy the quantized model file to the snapshot directory
	COPY mistral-7b-instruct-v0.1.Q4_K_M.gguf /root/.cache/huggingface/hub/models--TheBloke--Mistral-7B-Instruct-v0.1-GGUF/snapshots/731a9fc8f06f5f5e2db8a0cf9d256197eb6e05d1/

	# Expose port 8000 for FastAPI
	EXPOSE 8000

	# Command to start the FastAPI application
	CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]