Instructions to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Transformers:

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

pipe = pipeline("text-generation", model="npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S", dtype="auto")

llama-cpp-python

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S",
	filename="models-meta-llama-Meta-Llama-3.1-0.06K-70b-IQ_1S.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
# Run inference directly in the terminal:
llama-cli -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
# Run inference directly in the terminal:
llama-cli -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

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 npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
# Run inference directly in the terminal:
./llama-cli -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

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 npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

Use Docker

docker model run hf.co/npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

LM Studio
Jan

vLLM

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

SGLang

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S 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 "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S" \
    --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": "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S",
		"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 "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S" \
        --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": "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Ollama:
```
ollama run hf.co/npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
```

Unsloth Studio new

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S 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 npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S 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 npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S to start chatting

Pi new

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

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": "npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

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 npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

Run Hermes

hermes

Docker Model Runner
How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Docker Model Runner:
```
docker model run hf.co/npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S
```

Lemonade

How to use npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

Run and chat with the model

lemonade run user.Meta-Llama-3.1-70B-Instruct-IQ_1S-{{QUANT_TAG}}

List all available models

lemonade list

Model Information

The Llama 3.1 instruction tuned text only 70B model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

This repository stores a experimental IQ_1S quantized GGUF Llama 3.1 instruction tuned 70B model.

Model developer: Meta

Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

	Training Data	Params	Input modalities	Output modalities	Context length	GQA	Token count	Knowledge cutoff
Llama 3.1 (text only)	A new mix of publicly available online data.	70B	Multilingual Text	Multilingual Text and code	128k	Yes	15T+	December 2023

Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Quantization Information

Weight Quantization	PPL
FP16	4.1892 +/- 0.01430
IQ_1S	8.5005 +/- 0.03298

Dataset used for re-calibration: Mix of standard_cal_data

The generated imatrix can be downloaded from imatrix.dat

Usage: with llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S",
    filename="GGUF_FILE",
)

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

Downloads last month: 13

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Quantized

(116)

this model