Instructions to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Mistral-7B-Instruct-v0.1-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
	filename="mistral-7b-instruct-v0.1.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Mistral-7B-Instruct-v0.1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M

SGLang

How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF 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 "TheBloke/Mistral-7B-Instruct-v0.1-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheBloke/Mistral-7B-Instruct-v0.1-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with Ollama:
```
ollama run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-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 TheBloke/Mistral-7B-Instruct-v0.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheBloke/Mistral-7B-Instruct-v0.1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/Mistral-7B-Instruct-v0.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/Mistral-7B-Instruct-v0.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7B-Instruct-v0.1-GGUF-Q4_K_M

List all available models

lemonade list

Addressing Inconsistencies in Model Outputs: Understanding and Solutions

#13

by shivammehta - opened Nov 17, 2023

Discussion

shivammehta

Nov 17, 2023

•

edited Nov 17, 2023

When experimenting with this model, I've observed occasional discrepancies in its output. Sometimes it provides the correct response, and sometimes times it doesn't, even when presented with the same or similar questions. I have two inquiries: Why does this occur, and how can we address this issue?
Like Output Arrives at the correct Answer. (Occasionally does not arrive at the correct answer, the behavior is not 100% predictable.

Code -
from huggingface_hub import hf_hub_download
from langchain.llms import LlamaCpp

MODEL_ID = "TheBloke/Mistral-7B-Instruct-v0.1-GGUF""

CONTEXT_WINDOW_SIZE = 4096
MAX_NEW_TOKENS = 1024

model_path = hf_hub_download(
repo_id=MODEL_ID,
filename=MODEL_BASENAME,
resume_download=True,
cache_dir="./models",
)
kwargs = {
"model_path": model_path,
"n_ctx": CONTEXT_WINDOW_SIZE,
"max_tokens": MAX_NEW_TOKENS,
"n_gpu_layers":4
}
llm = LlamaCpp(
model_path=model_path,
temperature=0.1,
n_ctx=4096,
max_tokens=1024,
n_batch=100,
top_p=1,
verbose=True,
n_gpu_layers=100)

agent = create_csv_agent(llm, ['./Data/Employees.csv','./Data/Verticals.csv'], verbose=True)
response = agent.run("Which vertical name has the most number of resignations")
print(response)

QUERY:

What are the steps / measures to be taken to ensure that there is consistency in the final answer?
We have observed on various runs the paths to arriving at the final answer keep changing. Assuming the initial path that is chosen is a wrong path, how to ensure that the reasoning of the LLM takes corrective measures to finally arrive at the correct answer? (We have seen sometimes these corrective actions are infact taken..)

nlpsingh

Feb 7, 2024

I am also experiencing the same issue. I opened an issue for it as well: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/discussions/21

YaTharThShaRma999

Feb 7, 2024

@nlpsingh its probably because of your sampling parameters.

Like temperature, top p, min p, they basically can change output.

Higher usually means a bit more creative and better but it might change the response a bit too much sometimes.

Just lower the params it should be fine. With temp at 0 you will always get the same response but it might be a bit boring

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment