README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - argilla/CapybaraHermes-2.5-Mistral-7B
  - argilla/distilabeled-OpenHermes-2.5-Mistral-7B
base_model:
  - argilla/CapybaraHermes-2.5-Mistral-7B
  - argilla/distilabeled-OpenHermes-2.5-Mistral-7B
model-index:
  - name: KangalKhan-RawEmerald-7B
    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: 66.89
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          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: 85.75
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          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: 63.23
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          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: 57.58
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          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: 78.22
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          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: 62.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawEmerald-7B
          name: Open LLM Leaderboard

KangalKhan-RawEmerald-7B

I suggest using ChatML (Use whatever system prompt you like, this is just an example!):

<|im_start|>system
You are a friendly assistant.<|im_end|>
<|im_start|>user
Hello, what are you?<|im_end|>
<|im_start|>assistant
I am an AI language model designed to assist users with information and answer their questions. How can I help you today?<|im_end|>

Q4_K_S GGUF:
https://huggingface.co/Yuma42/KangalKhan-RawEmerald-7B-GGUF

More GGUF variants by mradermacher:
WARNING: I have observed that these versions output typos in rare cases. If you have the same problem, use my Q4_K_S GGUF above. https://huggingface.co/mradermacher/KangalKhan-RawEmerald-7B-GGUF

KangalKhan-RawEmerald-7B is a merge of the following models using LazyMergekit:

• argilla/CapybaraHermes-2.5-Mistral-7B
• argilla/distilabeled-OpenHermes-2.5-Mistral-7B

🧩 Configuration

models:
  - model: teknium/OpenHermes-2.5-Mistral-7B
    # no parameters necessary for base model
  - model: argilla/CapybaraHermes-2.5-Mistral-7B
    parameters:
      density: 0.6
      weight: 0.5
  - model: argilla/distilabeled-OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.6
      weight: 0.5
merge_method: ties
base_model: teknium/OpenHermes-2.5-Mistral-7B
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Yuma42/KangalKhan-RawEmerald-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

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.	69.09
AI2 Reasoning Challenge (25-Shot)	66.89
HellaSwag (10-Shot)	85.75
MMLU (5-Shot)	63.23
TruthfulQA (0-shot)	57.58
Winogrande (5-shot)	78.22
GSM8k (5-shot)	62.85