Safetensors
llama
falcon3
4-bit precision
gptq
drawing

Falcon3-7B-Instruct-GPTQ-Int4

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.

Falcon3-7B-Instruct achieves state-of-the-art results (at release's time) on reasoning, language understanding, instruction following, code and mathematics tasks. Falcon3-7B-Instruct supports 4 languages (English, French, Spanish, Portuguese) and a context length of up to 32K.

This repository contains the GPTQ-quantized 4-bit instruction-tuned 7B Falcon3 model.

Model Details

  • Architecture
    • Transformer-based causal decoder-only architecture
    • 28 decoder blocks
    • Grouped Query Attention (GQA) for faster inference: 12 query heads and 4 key-value heads
    • Wider head dimension: 256
    • High RoPE value to support long context understanding: 1000042
    • Uses SwiGLU and RMSNorm
    • 32K context length
    • 131K vocab size
  • Pretrained on 14 Teratokens of datasets comprising of web, code, STEM, high quality and mutlilingual data using 1024 H100 GPU chips
  • Posttrained on 1.2 million samples of STEM, conversational, code, safety and function call data
  • Supports EN, FR, ES, PT
  • Developed by Technology Innovation Institute
  • License: TII Falcon-LLM License 2.0
  • Model Release Date: December 2024
  • Quantization: GPTQ 4-bit

Getting started

Click to expand
from transformers import AutoTokenizer, AutoModelForCausalLM


model_name = "tiiuae/Falcon3-7B-Instruct-GPTQ-Int4"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many hours in one day?"

messages = [
    {"role": "system", "content": "You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Benchmarks

We report in the following table our internal pipeline benchmarks:

Benchmark Falcon3-7B-Instruct Falcon3-7B-Instruct-GPTQ-Int8 Falcon3-7B-Instruct-AWQ Falcon3-7B-Instruct-GPTQ-Int4
MMLU 67.7 67.6 66.4 65.6
MMLU-PRO 40.9 40.9 39.9 39.1
IFEval 75.1 77.0 74.8 72.2

Useful links

Technical Report

Coming soon....

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},
    url = {https://huggingface.co./blog/falcon3},
    author = {Falcon-LLM Team},
    month = {December},
    year = {2024}
}
Downloads last month
154
Safetensors
Model size
1.7B params
Tensor type
I32
·
FP16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for tiiuae/Falcon3-7B-Instruct-GPTQ-Int4

Quantized
(23)
this model

Collection including tiiuae/Falcon3-7B-Instruct-GPTQ-Int4