Instructions to use koesn/Llama3.1-8B-Cobalt-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use koesn/Llama3.1-8B-Cobalt-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="koesn/Llama3.1-8B-Cobalt-GGUF",
	filename="llama3.1-8b-cobalt.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use koesn/Llama3.1-8B-Cobalt-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

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 koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

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 koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Use Docker

docker model run hf.co/koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use koesn/Llama3.1-8B-Cobalt-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "koesn/Llama3.1-8B-Cobalt-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "koesn/Llama3.1-8B-Cobalt-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Ollama
How to use koesn/Llama3.1-8B-Cobalt-GGUF with Ollama:
```
ollama run hf.co/koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
```

Unsloth Studio

How to use koesn/Llama3.1-8B-Cobalt-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 koesn/Llama3.1-8B-Cobalt-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 koesn/Llama3.1-8B-Cobalt-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for koesn/Llama3.1-8B-Cobalt-GGUF to start chatting

How to use koesn/Llama3.1-8B-Cobalt-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use koesn/Llama3.1-8B-Cobalt-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

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 koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use koesn/Llama3.1-8B-Cobalt-GGUF with Docker Model Runner:
```
docker model run hf.co/koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K
```

Lemonade

How to use koesn/Llama3.1-8B-Cobalt-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull koesn/Llama3.1-8B-Cobalt-GGUF:Q2_K

Run and chat with the model

lemonade run user.Llama3.1-8B-Cobalt-GGUF-Q2_K

List all available models

lemonade list

Description

This repo contains GGUF format model files for Llama3.1-8B-Cobalt.

Files Provided

Name	Quant	Bits	File Size	Remark
llama3.1-8b-cobalt.Q2_K.gguf	Q2_K	2	3.18 GB	2.96G, +3.5199 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q3_K.gguf	Q3_K	3	4.02 GB	3.74G, +0.6569 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q4_0.gguf	Q4_0	4	4.66 GB	4.34G, +0.4685 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q4_K.gguf	Q4_K	4	4.92 GB	4.58G, +0.1754 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q5_K.gguf	Q5_K	5	5.73 GB	5.33G, +0.0569 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q6_K.gguf	Q6_K	6	6.60 GB	6.14G, +0.0217 ppl @ Llama-3-8B
llama3.1-8b-cobalt.Q8_0.gguf	Q8_0	8	8.54 GB	7.96G, +0.0026 ppl @ Llama-3-8B

Parameters

path	type	architecture	rope_theta	sliding_win	max_pos_embed
ValiantLabs/Llama3.1-8B-Cobalt	llama	LlamaForCausalLM	500000.0	null	131072

Original Model Card

Cobalt is a math-instruct model built on Llama 3.1 8b.

High quality math instruct performance within the Llama 3 Instruct chat format
Finetuned on synthetic math-instruct data generated with Llama 3.1 405b. Find the current version of the dataset here!

Version

This is the 2024-08-16 release of Cobalt for Llama 3.1 8b.

Help us and recommend Cobalt to your friends! We're excited for more Cobalt releases in the future.

Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 :)

Prompting Guide

Cobalt uses the Llama 3.1 Instruct prompt format. The example script below can be used as a starting point for general chat:

import transformers import torch

model_id = "ValiantLabs/Llama3.1-8B-Cobalt"

pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", )

messages = [ {"role": "system", "content": "You are Cobalt, expert math AI."}, {"role": "user", "content": "I'm buying a $50 shirt and a $80 pair of pants, both currently at a 25% discount. How much will I pay?"} ]

outputs = pipeline( messages, max_new_tokens=1024, )

print(outputs[0]["generated_text"][-1])

The Model

Cobalt is built on top of Llama 3.1 8b Instruct, using math-instruct data to supplement math-instruct performance using Llama 3.1 Instruct prompt style.

Our current version of the Cobalt math-instruct dataset is sequelbox/Polytope, supplemented with a small selection of data from LDJnr/Pure-Dove for general chat consistency.

Cobalt is created by Valiant Labs.

Check out our HuggingFace page for Shining Valiant 2 and our other Build Tools models for creators!

We care about open source. For everyone to use.

We encourage others to finetune further from our models.

Downloads last month: 42

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

4-bit

6-bit

8-bit

Model tree for koesn/Llama3.1-8B-Cobalt-GGUF

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(865)

this model

koesn
/

Llama3.1-8B-Cobalt-GGUF