Instructions to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Statuo/Mistral_Nemo_Instruct_EXL2_4bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Statuo/Mistral_Nemo_Instruct_EXL2_4bpw")
model = AutoModelForCausalLM.from_pretrained("Statuo/Mistral_Nemo_Instruct_EXL2_4bpw", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Statuo/Mistral_Nemo_Instruct_EXL2_4bpw

SGLang

How to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Statuo/Mistral_Nemo_Instruct_EXL2_4bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw 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 Statuo/Mistral_Nemo_Instruct_EXL2_4bpw 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 Statuo/Mistral_Nemo_Instruct_EXL2_4bpw to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Statuo/Mistral_Nemo_Instruct_EXL2_4bpw to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Statuo/Mistral_Nemo_Instruct_EXL2_4bpw",
    max_seq_length=2048,
)

Docker Model Runner
How to use Statuo/Mistral_Nemo_Instruct_EXL2_4bpw with Docker Model Runner:
```
docker model run hf.co/Statuo/Mistral_Nemo_Instruct_EXL2_4bpw
```

Statuo commited on Jul 18, 2024

Commit

040f4a6

verified ·

1 Parent(s): cb69c4c

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -23

README.md CHANGED Viewed

@@ -9,29 +9,12 @@ tags:
 - transformers
 ---
-# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
-We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
-## ✨ Finetune for Free
-All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
-| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
-|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
-| **Llama-3 8b**      | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing)               | 2.4x faster | 58% less |
-| **Gemma 7b**      | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing)               | 2.4x faster | 58% less |
-| **Mistral 7b**    | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing)               | 2.2x faster | 62% less |
-| **Llama-2 7b**      | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing)               | 2.2x faster | 43% less |
-| **TinyLlama**  | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)              | 3.9x faster | 74% less |
-| **CodeLlama 34b** A100   | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing)              | 1.9x faster | 27% less |
-| **Mistral 7b** 1xT4  | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
-| **DPO - Zephyr**     | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing)               | 1.9x faster | 19% less |
-- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
-- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
-- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

 - transformers
 ---
+# I quanted this from the Unsloth upload for Mistral Nemo Instruct.
+[You can find the link here](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)
+[This is for the base Mistral Nemo Instruct Model](nvidia/Mistral-NeMo-12B-Instruct)
+EXL2 quanting seemed to work. I ran a few tests on it and it seemed to have zero issues generating text up to 32k context size. I did not try higher than that, but uploading so folks can start testing this. Pleasantly surprised for a roleplay capacity as it seemed to latch onto character traits very well.
+[8BPW](https://huggingface.co/Statuo/Mistral_Nemo_Instruct_EXL2_8bpw)
+[6BPW](https://huggingface.co/Statuo/Mistral_Nemo_Instruct_EXL2_6bpw)