Instructions to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

llama-cpp-python

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2",
	filename="Mistral-7B-Instruct-v0.3-q-Chemistry-v0.2.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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
# Run inference directly in the terminal:
llama cli -hf jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
# Run inference directly in the terminal:
llama cli -hf jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
# Run inference directly in the terminal:
./llama-cli -hf jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

Use Docker

docker model run hf.co/jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

LM Studio
Jan
Ollama
How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with Ollama:
```
ollama run hf.co/jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
```

Unsloth Studio

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 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 jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 to start chatting

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with Docker Model Runner:
```
docker model run hf.co/jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2
```

Lemonade

How to use jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jarvisloh/Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2

Run and chat with the model

lemonade run user.Mistral-7B-Instruct-v0.3-q-Chemistry-gguf-v0.2-{{QUANT_TAG}}

List all available models

lemonade list

jarvisloh commited on Feb 7, 2025

Commit

d29dc56

verified ·

1 Parent(s): fc526c6

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -1

README.md CHANGED Viewed

@@ -6,4 +6,31 @@ language:
 base_model:
 - mistralai/Mistral-7B-Instruct-v0.3
 library_name: mlx
----

 base_model:
 - mistralai/Mistral-7B-Instruct-v0.3
 library_name: mlx
+---
+Finetuned on SmolInstruct's property prediction instruction dataset and HoneyBee's instruction dataset.
+[LoRA Config Parameters]
+train: true,
+fine_tune_type: lora,
+seed: 0,
+num_layers: 16,
+batch_size: 2,
+iters: 1000,
+val_batches: 25,
+learning_rate: 1e-5,
+steps_per_report: 10,
+steps_per_eval: 200,
+resume_adapter_file: null,
+adapter_path: "adapters",
+save_every: 100,
+test: false,
+test_batches: 100,
+max_seq_length: 2048,
+grad_checkpoint: false,
+lora_parameters:
+  keys: ["self_attn.q_proj", "self_attn.v_proj"]
+  rank: 32
+  alpha: 64
+  dropout: 0.0
+  scale: 20.0