Instructions to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF", dtype="auto")

llama-cpp-python

How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF",
	filename="mistral-7b-inst-0.2-bulleted-notes.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_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 cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_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 cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_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 cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M

Use Docker

docker model run hf.co/cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with Ollama:
```
ollama run hf.co/cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
```

Unsloth Studio new

How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_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 cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_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 cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF to start chatting

Docker Model Runner
How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with Docker Model Runner:
```
docker model run hf.co/cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M
```

Lemonade

How to use cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF-Q4_K_M

List all available models

lemonade list

Mistral 7b Instruct v0.2 - Bulleted Notes

https://github.com/cognitivetech/ollama-ebook-summary

Template:

ChatML

Modelfile:

<|im_start|>system
<|im_start|>user
{{ .Prompt }} <|im_end|>
<|im_start|>assistant
{{ .Response }}<|im_end|>
"
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
PARAMETER num_ctx 8000
PARAMETER num_gpu -1
PARAMETER num_predict 4000

Uploaded model

Developed by: cognitivetech
License: apache-2.0
Finetuned from model : mistralai/Mistral-7B-Instruct-v0.2

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 841

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Inference Providers NEW

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

Model tree for cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF

Base model

mistralai/Mistral-7B-Instruct-v0.2

Quantized

(100)

this model

Space using cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF 1

Collection including cognitivetech/Mistral-7b-Inst-0.2-Bulleted-Notes_GGUF

Mistral Instruct Bulleted Notes v0.2

Collection

https://huggingface.co/blog/cognitivetech/bulleted-notes-ebook-summary • 3 items • Updated Aug 10, 2024 • 1