README.md

metadata

license: cc-by-sa-4.0
model-index:
  - name: Synatra-10.7B-v0.4
    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: 64.93
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          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: 82.47
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          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: 62.5
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          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: 51.11
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          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: 81.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          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: 50.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-10.7B-v0.4
          name: Open LLM Leaderboard

Synatra-10.7B-v0.4🐧

Join our discord

Server Link

License

The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included cc-by-sa-4.0 license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.

Model Details

Base Model
upstage/SOLAR-10.7B-v1.0

Trained On
A100 80GB * 1

Instruction format

It follows Alpaca format.

Model Benchmark

Ko-LLM-Leaderboard

On Benchmarking...

Implementation Code

Since, chat_template already contains insturction format above. You can use the code below.

from transformers import AutoModelForCausalLM, AutoTokenizer

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

model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-10.7B-v0.4")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-10.7B-v0.4")

messages = [
    {"role": "user", "content": "바나나는 원래 하얀색이야?"},
]

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])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	65.48
AI2 Reasoning Challenge (25-Shot)	64.93
HellaSwag (10-Shot)	82.47
MMLU (5-Shot)	62.50
TruthfulQA (0-shot)	51.11
Winogrande (5-shot)	81.85
GSM8k (5-shot)	50.04