README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
datasets:
  - HuggingFaceH4/ultrachat_200k
  - openchat/openchat_sharegpt4_dataset
  - Open-Orca/SlimOrca
inference: false
model-index:
  - name: falcon-rw-1b-chat
    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: 35.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          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: 61.12
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          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: 24.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          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: 39.62
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          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: 61.72
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          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: 1.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
          name: Open LLM Leaderboard
pipeline_tag: text-generation

🌟 Falcon-RW-1B-Chat

Falcon-RW-1B-Chat is a conversational model with 1 billion parameters. It's a further refinement of the Falcon-RW-1B-Instruct-OpenOrca, trained on selected data from the HuggingFaceH4/ultrachat_200k and openchat/openchat_sharegpt4_dataset datasets.

✨Try it out at our Tiny Chat space running on free-tier hardware!✨

The underlying Falcon-RW-1B-Instruct-OpenOrca model is built on the Falcon-RW-1B, a causal decoder-only model. It has been instruction-finetuned using the Open-Orca/SlimOrca dataset.

🎯 Purpose

The Falcon-RW-1B-Chat aims to add conversational capabilities to the Falcon-RW-1B-Instruct-OpenOrca model. This initiative is driven by the need for a smaller, open-source, instruction-finetuned, ready-to-use model, suitable for users with limited computational resources, like lower-end consumer GPUs.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	37.37
AI2 Reasoning Challenge (25-Shot)	35.58
HellaSwag (10-Shot)	61.12
MMLU (5-Shot)	24.51
TruthfulQA (0-shot)	39.62
Winogrande (5-shot)	61.72
GSM8k (5-shot)	1.67

📖 Example Code

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "ericzzz/falcon-rw-1b-chat"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, device_map="auto", torch_dtype=torch.bfloat16
)

chat_history = [
    {"role": "user", "content": "Hello!"},
    {"role": "assistant", "content": "Hello! How can I assist you today?"},
    {"role": "user", "content": "Explain what AI is."},
]

input_ids = tokenizer.apply_chat_template(
    chat_history, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
output_tokens = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.7,
    repetition_penalty=1.05,
    max_new_tokens=200,
)
output_text = tokenizer.decode(
    output_tokens[0][len(input_ids[0]) :], skip_special_tokens=True
)

print(output_text)

⚠️ Limitations

This model may generate inaccurate or misleading information and is prone to hallucination, creating plausible but false narratives. It lacks the ability to discern factual content from fiction and may inadvertently produce biased, harmful or offensive content. Its understanding of complex, nuanced queries is limited. Users should be aware of this and verify any information obtained from the model.

The model is provided 'as is' without any warranties, and the creators are not liable for any damages arising from its use. Users are responsible for their interactions with the model.

📬 Contact

For further inquiries or feedback, please contact at eric.fu96@aol.com.