README.md

metadata

license: apache-2.0
model-index:
  - name: West-Ramen-7Bx4
    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: 67.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          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: 85.52
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          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: 62.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          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: 61
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          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: 81.22
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          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: 58
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mayacinka/West-Ramen-7Bx4
          name: Open LLM Leaderboard

🧩 Configuration

base_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
gate_mode: hidden 
dtype: bfloat16 
experts:
  - source_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
    positive_prompts:
      - "instructions"
      - "concise"
      - "straightforward"
      - "helpful"
      - "assistant"
    negative_prompts:
      - "vague"
      - "inaccurate"
      - "verbose"
      - "complicated"
      - "speculative"
  - source_model: /home/Ubuntu/Desktop/mergekit/models/NeuralOmniWestBeaglake-7B
    positive_prompts:
      - "storytelling"
      - "role play"
      - "imagine"
      - "artistic"
      - "narrative"
  - source_model: /home/Ubuntu/Desktop/mergekit/models/Kunoichi-DPO-v2-7B
    positive_prompts:
      - "reason"
      - "think step by step"
      - "logic"
      - "knowledge"
    negative_prompts:
      - "artistic"
      - "speculative"
      - "playful"
  - source_model: /home/Ubuntu/Desktop/mergekit/models/Starling-LM-7B-alpha
    positive_prompts:
      - "code"
      - "python"
      - "javascript"
      - "react"
      - "clear"
      - "programming"
    negative_prompts:
      - "error"
      - "art"
      - "role play"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mayacinka/West-Ramen-7Bx4"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.33
AI2 Reasoning Challenge (25-Shot)	67.58
HellaSwag (10-Shot)	85.52
MMLU (5-Shot)	62.69
TruthfulQA (0-shot)	61.00
Winogrande (5-shot)	81.22
GSM8k (5-shot)	58.00