Instructions to use tiiuae/Falcon3-1B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon3-1B-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon3-1B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tiiuae/Falcon3-1B-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tiiuae/Falcon3-1B-Instruct-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 tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tiiuae/Falcon3-1B-Instruct-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 tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tiiuae/Falcon3-1B-Instruct-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 tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tiiuae/Falcon3-1B-Instruct-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 tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use tiiuae/Falcon3-1B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon3-1B-Instruct-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": "tiiuae/Falcon3-1B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

SGLang

How to use tiiuae/Falcon3-1B-Instruct-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 "tiiuae/Falcon3-1B-Instruct-GGUF" \
    --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": "tiiuae/Falcon3-1B-Instruct-GGUF",
		"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 "tiiuae/Falcon3-1B-Instruct-GGUF" \
        --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": "tiiuae/Falcon3-1B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tiiuae/Falcon3-1B-Instruct-GGUF with Ollama:
```
ollama run hf.co/tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop

How to use tiiuae/Falcon3-1B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

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": "tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tiiuae/Falcon3-1B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use tiiuae/Falcon3-1B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Falcon3-1B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tiiuae/Falcon3-1B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

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 tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tiiuae/Falcon3-1B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M

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 "tiiuae/Falcon3-1B-Instruct-GGUF:Q4_K_M" \
  --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"

Slim Frikha

ybelkada commited on Jan 14, 2025

Commit

fc404df

verified ·

1 Parent(s): f192894

(fix): Aligning quantized models tokenizer with base models ones (#3)

Browse files

- (fix): Aligning quantized models tokenizer with base models ones (b3954f619d0b8cae24b2d1d4f3cfd31883b10dfb)

Co-authored-by: Younes Belkada <ybelkada@users.noreply.huggingface.co>

Files changed (9) hide show

Falcon3-1B-Instruct-f16.gguf +2 -2
Falcon3-1B-Instruct-q2_k.gguf +2 -2
Falcon3-1B-Instruct-q3_k_m.gguf +2 -2
Falcon3-1B-Instruct-q4_0.gguf +2 -2
Falcon3-1B-Instruct-q4_k_m.gguf +2 -2
Falcon3-1B-Instruct-q5_0.gguf +2 -2
Falcon3-1B-Instruct-q5_k_m.gguf +2 -2
Falcon3-1B-Instruct-q6_k.gguf +2 -2
Falcon3-1B-Instruct-q8_0.gguf +2 -2

Falcon3-1B-Instruct-f16.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d5a0848ace5a1faebfe517744e8b505de1952210d951f93e39e93118e1b5c7
-size 3343708192

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6adc50e54e1fc7193f0d0f4fcb6a81c106d4a8cb9a317547ecadcccdb0dd8fa
+size 3343710336

Falcon3-1B-Instruct-q2_k.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22c6dfcd910cd4beed538254acfd597c9285d9c3adb9944d34f6a012f73dc2e
-size 727085088

 version https://git-lfs.github.com/spec/v1
+oid sha256:a2c2645263d17b1277627eb8cb16296138bdadcf47a0a34ee57e349bf7e6c7f2
+size 224950400

Falcon3-1B-Instruct-q3_k_m.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129f95cb6c7c146c05fb3aa6fca855fcc51ebc3e571ad7820ff69ad9db0e0e8c
-size 884961312

 version https://git-lfs.github.com/spec/v1
+oid sha256:60048f391f09c8ff354f207b12894e63e640b6dca9ba3bdec379204f74b8de65
+size 884963456

Falcon3-1B-Instruct-q4_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc26bf2f14fb7363007623362c9a935f90ef45ca9f4a38b49d19faebdba4220
-size 1013248032

 version https://git-lfs.github.com/spec/v1
+oid sha256:3b46b6e6e7c98208328c41522b9508a475aa667769b8ce0014eebe45a94a1899
+size 1013250176

Falcon3-1B-Instruct-q4_k_m.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75ba88610fb333f16ab19e8ef591a63f3f03d1e4beffd0d2a978a851401d32f
-size 1057042464

 version https://git-lfs.github.com/spec/v1
+oid sha256:54a4d303f5fb238db640433a61a600e308bfbb40cca2d7b451092e247df46616
+size 1057044608

Falcon3-1B-Instruct-q5_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3234db54a672421f4b7aa4b312e42a14f4e056e247d306104373fb6d774351c6
-size 1188360224

 version https://git-lfs.github.com/spec/v1
+oid sha256:041c14673e373d2714da69ae10aa239db390c65ae4327d7420e1027eb5c6a9de
+size 1188362368

Falcon3-1B-Instruct-q5_k_m.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6f4e0d16b12d8482679b9581c53e5773f19b6a11d036f2bc117d44f93c6fad
-size 1210920992

 version https://git-lfs.github.com/spec/v1
+oid sha256:3cc311d49fef58586194b61316c907b3da7f83c94ccf7c2b158e1b1710e7df86
+size 1210923136

Falcon3-1B-Instruct-q6_k.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c10e86a1e256387b51268e8a5e963513e29af3884eee3094f5422c445c9883a
-size 1374416928

 version https://git-lfs.github.com/spec/v1
+oid sha256:959bd1814873fd80b682a9094416c2b809fe0184917d408f651377cf07684570
+size 1374419072

Falcon3-1B-Instruct-q8_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e80a4c818408e554748d7792ce9768e33e4cf2df9d9b2fa61f155118de467d
-size 1778708512

 version https://git-lfs.github.com/spec/v1
+oid sha256:dda44709157103fc272ea3c44ae0deb7fbec5b2d82b313362680dec08e66f57a
+size 1778710656