jncraton/Falcon3-7B-Instruct-ct2-int8

Falcon3-7B-Instruct

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

This repository contains the Falcon3-7B-Instruct. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks. Falcon3-7B-Instruct supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K.

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
• Postrained on 1.2 million samples of STEM, conversations, 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

Getting started

Click to expand

from transformers import AutoTokenizer, AutoModelForCausalLM


from transformers import AutoModelForCausalLM, AutoTokenizer

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

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.

• We use lm-evaluation harness.
• We report raw scores obtained by applying chat template without fewshot_as_multiturn (unlike Llama3.1).
• We use same batch-size across all models.

Category	Benchmark	Llama-3.1-8B-Instruct	Qwen2.5-7B-Instruct	Falcon3-7B-Instruct
General	MMLU (5-shot)	55.9	72.4	68
	MMLU-PRO (5-shot)	21.8	35.8	40.7
	IFEval	78.8	74.7	76.5
Math	GSM8K (5-shot)	78.1	77.5	79.1
	GSM8K (8-shot, COT)	79.8	72.7	80.9
	MATH Lvl-5 (4-shot)	10.4	26	29.4
Reasoning	Arc Challenge (25-shot)	46.6	55.7	65.9
	GPQA (0-shot)	33.6	31.9	32
	GPQA (0-shot, COT)	9.6	13.8	22.3
	MUSR (0-shot)	38.6	40.7	46.4
	BBH (3-shot)	43.7	53.9	52.4
CommonSense Understanding	PIQA (0-shot)	78.9	73.7	78.8
	SciQ (0-shot)	80.2	50.9	94.7
	Winogrande (0-shot)	-	-	70.4
	OpenbookQA (0-shot)	46.2	42.4	45.8
Instructions following	MT-Bench (avg)	7.9	8.5	8.4
	Alpaca (WC)	26.6	31.5	26.1
Tool use	BFCL AST (avg)	90.6	91.4	72.3

Technical Report

Coming soon....

Citation

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

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