RichardErkhov/BarraHome_-_zephyr-dpo-v2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

zephyr-dpo-v2 - GGUF

• —Model creator: https://huggingface.co/BarraHome/
• —Original model: https://huggingface.co/BarraHome/zephyr-dpo-v2/

Original model description: --- language:

• —en
• —es license: mit library_name: transformers tags:
• —text-generation-inference
• —transformers
• —unsloth
• —mistral
• —trl datasets:
• —jondurbin/truthy-dpo-v0.1
• —BarraHome/ultrafeedbackbinarized basemodel: BarraHome/zephyr-dpo-4bit pipeline_tag: text-classification model-index:
• —name: zephyr-dpo-v2 results:
• —task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2arc config: ARC-Challenge split: test args: numfew_shot: 25 metrics:
• —type: accnorm value: 57.85 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: numfewshot: 10 metrics:
• —type: accnorm value: 82.72 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: numfewshot: 5 metrics:
• —type: acc value: 58.61 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthfulqa config: multiplechoice split: validation args: numfewshot: 0 metrics:
• —type: mc2 value: 56.16 source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winograndexl split: validation args: numfew_shot: 5 metrics:
• —type: acc value: 74.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: numfewshot: 5 metrics:
• —type: acc value: 30.25 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=BarraHome/zephyr-dpo-v2 name: Open LLM Leaderboard ---

Uploaded model

• —Developed by: BarraHome
• —License: apache-2.0
• —Finetuned from model : BarraHome/zephyr-dpo-4bit

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here