Text Generation
GGUF
English
conversational
brittlewis12's picture
Create README.md
7dcb18d verified
metadata
base_model: snorkelai/Snorkel-Mistral-PairRM-DPO
datasets:
  - snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
  - HuggingFaceH4/ultrafeedback_binarized
license: apache-2.0
language:
  - en
model_creator: snorkelai
model_name: Snorkel-Mistral-PairRM-DPO
model_type: mistral
inference: false
pipeline_tag: text-generation
prompt_template: |
  <|im_start|>system
  {{system_message}}<|im_end|>
  <|im_start|>user
  {{prompt}}<|im_end|>
  <|im_start|>assistant
quantized_by: brittlewis12

Snorkel-Mistral-PairRM-DPO GGUF

Original model: Snorkel-Mistral-PairRM-DPO Model creator: Snorkel AI

This repo contains GGUF format model files for Snorkel AI’s Snorkel-Mistral-PairRM-DPO.

With this demonstration, we focus on the general approach to alignment. Thus, we use a general-purpose reward model - the performant PairRM model. We use the Mistral-7B-Instruct-v0.2 model as our base LLM.

What is GGUF?

GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Converted using llama.cpp b1960 (26d6076)

Prompt template: ChatML

<|im_start|>system
{{system_message}}<|im_end|>
<|im_start|>user
{{prompt}}<|im_end|>
<|im_start|>assistant

Download & run with cnvrs on iPhone, iPad, and Mac!

cnvrs.ai

cnvrs is the best app for private, local AI on your device:

  • create & save Characters with custom system prompts & temperature settings
  • download and experiment with any GGUF model you can find on HuggingFace!
  • make it your own with custom Theme colors
  • powered by Metal ⚡️ & Llama.cpp, with haptics during response streaming!
  • try it out yourself today, on Testflight!
  • follow cnvrs on twitter to stay up to date

Original Model Evaluations:

On Alpaca-Eval 2.0:

After applying the above methodology:

  • This model scored 30.22 - ranked 3rd and the highest for an open-source base model at the time of publication.