Instructions to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Transformers:

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

pipe = pipeline("text-generation", model="alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit")
model = AutoModelForCausalLM.from_pretrained("alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit", 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

llama.cpp

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit 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 alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
# Run inference directly in the terminal:
llama cli -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
# Run inference directly in the terminal:
llama cli -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

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 alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
# Run inference directly in the terminal:
./llama-cli -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

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 alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Use Docker

docker model run hf.co/alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

LM Studio
Jan

vLLM

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

SGLang

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit 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 "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit" \
    --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": "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit",
		"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 "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit" \
        --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": "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Ollama:
```
ollama run hf.co/alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
```
Unsloth Desktop

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Docker Model Runner:
```
docker model run hf.co/alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit
```

Lemonade

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Run and chat with the model

lemonade run user.Falcon3-10B-Instruct-1.58bit-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

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 alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

TL;DR
Model Details
Training Details
Usage
Evaluation
Citation

TL;DR

Model Details

Model Description

Developed by: https://www.tii.ae
Model type: Causal decoder-only - instruct / chat version
Architecture: Pure-transformer - 1.58bit version
Language(s) (NLP): Mainly English
License: TII Falcon License 2.0

Training details

The model has been trained following the training strategies from the recent 1-bit LLM HF blogpost and 1-bit LLM paper. For more details about the training protocol of this model, please refer to the Falcon-3 technical report, section Compression.

Usage

Currently to use this model you can either rely on Hugging Face transformers library or BitNet library. You can also play with the model using the falcon-1.58bit playground (only for the 7B instruct version).

🤗 transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tiiuae/Falcon3-7B-Instruct-1.58bit"

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.bfloat16,
).to("cuda")

# Perform text generation

BitNet

git clone https://github.com/microsoft/BitNet && cd BitNet
pip install -r requirements.txt
python setup_env.py --hf-repo tiiuae/Falcon3-10B-Instruct-1.58bit -q i2_s
python run_inference.py -m models/Falcon3-10B-1.58bit/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv

Evaluation

We report in the following table our internal pipeline benchmarks:

Note evaluation results are normalized score from v2 leaderboard tasks - reported results of original models in the blogpost are raw scores

Benchmark	Llama3-8B-1.58-100B-tokens	Falcon3-10B-Instruct-1.58bit
IFEval	17.91	54.37
MUSR	4.87	2.57
GPQA	1.83	4.27
BBH	5.36	6.59
MMLU-PRO	2.78	6.62
MATH	0.26	2.44
Average	5.5	12.81

Useful links

View our release blogpost.
Feel free to join our discord server if you have any questions or to interact with our researchers and developers.

Citation

If the Falcon3 family of models were helpful to your work, feel free to give us a cite.

@misc{Falcon3,
    title = {The Falcon 3 Family of Open Models},
    author = {Falcon-LLM Team},
    month = {December},
    year = {2024}
}

Downloads last month: 37

GGUF

Model size

10B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Base model

tiiuae/Falcon3-10B-Base

Finetuned

tiiuae/Falcon3-10B-Instruct

Quantized

(42)

this model

Paper for alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 630

alfonsogarciacaro
/

Falcon3-10B-Instruct-1.58bit

Table of Contents

TL;DR

Model Details

Model Description

Training details

Usage

🤗 transformers

BitNet

Evaluation

Useful links

Citation

Model tree for alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

Paper for alfonsogarciacaro/Falcon3-10B-Instruct-1.58bit

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits