falcon-11B / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
5ed1770 verified
|
raw
history blame
11.9 kB
metadata
language:
  - en
  - de
  - es
  - fr
datasets:
  - tiiuae/falcon-refinedweb
inference: false
model-index:
  - name: falcon-11B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 59.73
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 82.91
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 58.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 52.56
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 78.3
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 53.83
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tiiuae/falcon-11B
          name: Open LLM Leaderboard

πŸš€ Falcon2-11B

Falcon2-11B is a 11B parameters causal decoder-only model built by TII and trained over 5,000B tokens of RefinedWeb enhanced with curated corpora. The model is made available under the TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.

Paper coming soon 😊.

πŸ€— To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading this great blogpost fron HF!

⚠️ This is a raw, pretrained model, which should be further finetuned for most usecases.

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-11B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
)
sequences = pipeline(
   "Can you explain the concepts of Quantum Computing?",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

πŸ’₯ Falcon LLMs require PyTorch 2.0 for use with transformers!

For fast inference with Falcon, check-out Text Generation Inference! Read more in this blogpost.

Model Card for Falcon2-11B

Model Details

Model Description

  • Developed by: https://www.tii.ae
  • Model type: Causal decoder-only
  • Language(s) (NLP): English, German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish
  • License: TII Falcon License 2.0

Model Source

  • Paper: coming soon.

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.

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-11B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
sequences = pipeline(
   "Can you explain the concepts of Quantum Computing?",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Training Details

Training Data

Falcon2-11B was trained over 5,000B tokens of RefinedWeb, a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. It followed a four stage training strategy. The first three stages were focused on increasing the context length, from to 2048 to 4096 and finally to 8192 tokens. The last stage aimed to further enhance performance using only high quality data.

Overall, the data sources included RefinedWeb-English, Refined Web-Europe (cs, de, es, fr, it, nl, pl, pt, ro, sv), high quality technical data, code data, and conversational data extracted from public sources.

The training stages were as follows:

Stage Context length Tokens
Stage 1 2048 4500 B
Stage 2 4096 250 B
Stage 3 8192 250 B
Stage 4 8192 500 B

The data was tokenized with the Falcon-7B/11B tokenizer.

Training Procedure

Falcon2-11B was trained on 1024 A100 40GB GPUs for the majority of the training, using a 3D parallelism strategy (TP=8, PP=1, DP=128) combined with ZeRO and Flash-Attention 2.

Training Hyperparameters

Hyperparameter Value Comment
Precision bfloat16
Optimizer AdamW
Max learning rate 3.7e-4 Following a linear warm-up, then cosine decay to 1.89e-5 across 4500 B tokens.
Weight decay 1e-1
Z-loss 1e-4
Batch size Variable Batch size was gradually increased during the training

Speeds, Sizes, Times

The model training took roughly two months.

Evaluation

English Benchmark Value
ARC-Challenge-25shots 59.73
HellaSwag-10shots 82.91
MMLU-5shots 58.37
Winogrande-5shots 78.30
TruthfulQA-0shot 52.56
GSM8k-5shots 53.83
ARC-Challenge-0shot 50.17
ARC-Easy-0shot 77.78
Hellaswag-0shot 82.07

We thank the leaderboard team from HuggingFace for providing an official evaluation of our model on the leaderboard tasks.

Technical Specifications

Model Architecture and Objective

Falcon2-11B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).

The architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:

Hyperparameter Value Comment
Layers 60
d_model 4096
head_dim 128
Vocabulary 65024
Sequence length 8192 During stages 3 and 4

Compute Infrastructure

Hardware

Falcon2-11B was trained on AWS SageMaker, using on average 1024 A100 40GB GPUs in 128 p4d instances.

Software

Falcon2-11B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO, high-performance Triton kernels and FlashAttention-2. More details about the distributed training strategy can be found in Almazrouei et.al.

Citation

Paper coming soon 😊.

License

Falcon2-11B is licenced under TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.

Contact

falconllm@tii.ae

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 64.28
AI2 Reasoning Challenge (25-Shot) 59.73
HellaSwag (10-Shot) 82.91
MMLU (5-Shot) 58.37
TruthfulQA (0-shot) 52.56
Winogrande (5-shot) 78.30
GSM8k (5-shot) 53.83