Instructions to use thesven/falcon-11B-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thesven/falcon-11B-GPTQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="thesven/falcon-11B-GPTQ-4bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thesven/falcon-11B-GPTQ-4bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("thesven/falcon-11B-GPTQ-4bit", trust_remote_code=True)
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

vLLM

How to use thesven/falcon-11B-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thesven/falcon-11B-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thesven/falcon-11B-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thesven/falcon-11B-GPTQ-4bit

SGLang

How to use thesven/falcon-11B-GPTQ-4bit 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 "thesven/falcon-11B-GPTQ-4bit" \
    --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": "thesven/falcon-11B-GPTQ-4bit",
		"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 "thesven/falcon-11B-GPTQ-4bit" \
        --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": "thesven/falcon-11B-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thesven/falcon-11B-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/thesven/falcon-11B-GPTQ-4bit
```

Model Card for Model ID

Model Details

Model Description

This model is a quantized version of Falcon2-11B by tiiuae. Quantization was performed with Auto-GPTQ to 4bit.

Developed by: TIIIUAE
Quantised by: Michael Svendsen

Getting Started

from transformers import AutoTokenizer, AutoModelForCausalLM, GPTQConfig

pretrained_model_name = "thesven/falcon-11B-GPTQ-4bit"
device = "cuda:0"

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name)

# Load the model with the specified configuration and move to device
model = AutoModelForCausalLM.from_pretrained(
    pretrained_model_name,
    device_map="auto",
)
# Set EOS token ID
model.eos_token_id = tokenizer.eos_token_id

# Move model to the specified device
model.to(device)

# Define the input text
input_text = "Why is the sky blue?"

# Encode the input text
input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)

# Generate output
output = model.generate(input_ids, max_length=1000)

# Decode the generated output
decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)

# Print the decoded output
for i, sequence in enumerate(decoded_output):
    print(f"Generated Sequence {i+1}: {sequence}")

License

Falcon2-11B is licenced under [TII Falcon License 2.0(https://falconllm-staging.tii.ae/falcon-2-terms-and-conditions.html), the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.

Uses

Direct Use

Research on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)

Out-of-Scope Use

Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.

Bias, Risks, and Limitations

Falcon2-11B is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.

Recommendations

We recommend users of Falcon2-11B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.

Downloads last month: 5

Safetensors

Model size

11B params

Tensor type

I32

F16

Dataset used to train thesven/falcon-11B-GPTQ-4bit

Collection including thesven/falcon-11B-GPTQ-4bit

GPTQ Quants

Collection

15 items • Updated Sep 13, 2024