README.md

metadata

license: apache-2.0
datasets:
  - openagi-project/OpenAGI-set-dpo-v0.1
base_model: freecs/ThetaWave-7B-v0.1
model-index:
  - name: OpenAGI-7B-v0.1
    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: 66.72
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          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: 86.13
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          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: 63.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          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: 69.55
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          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: 79.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          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: 56.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=openagi-project/OpenAGI-7B-v0.1
          name: Open LLM Leaderboard

OpenAGI-7B-v0.1

DPO tuned on a small set of GPT4 generated responses.

Give it a try:

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"  # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("openagi-project/OpenAGI-7B-v0.1")
tokenizer = AutoTokenizer.from_pretrained("openagi-project/OpenAGI-7B-v0.1")

messages = [
    {"role": "user", "content": "Who are you?"},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

" My goal as the founder of FreeCS.org is to establish an Open-Source AI Research Lab driven by its Community. Currently, I am the sole contributor at FreeCS.org. If you share our vision, we welcome you to join our community and contribute to our mission at freecs.org/#community. "
|- GR

If you'd like to support this project, kindly consider making a donation.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.34
AI2 Reasoning Challenge (25-Shot)	66.72
HellaSwag (10-Shot)	86.13
MMLU (5-Shot)	63.53
TruthfulQA (0-shot)	69.55
Winogrande (5-shot)	79.48
GSM8k (5-shot)	56.63