You can deploy this model and start earning money today!

RichardErkhov/
rwitz_-_dec10-gguf

Name: rwitz_-_dec10-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

dec10 - GGUF

Model creator: https://huggingface.co/rwitz/
Original model: https://huggingface.co/rwitz/dec10/

Name	Quant method	Size
dec10.Q2_K.gguf	Q2_K	2.53GB
dec10.IQ3_XS.gguf	IQ3_XS	2.81GB
dec10.IQ3_S.gguf	IQ3_S	2.96GB
dec10.Q3_K_S.gguf	Q3_K_S	2.95GB
dec10.IQ3_M.gguf	IQ3_M	3.06GB
dec10.Q3_K.gguf	Q3_K	3.28GB
dec10.Q3_K_M.gguf	Q3_K_M	3.28GB
dec10.Q3_K_L.gguf	Q3_K_L	3.56GB
dec10.IQ4_XS.gguf	IQ4_XS	3.67GB
dec10.Q4_0.gguf	Q4_0	3.83GB
dec10.IQ4_NL.gguf	IQ4_NL	3.87GB
dec10.Q4_K_S.gguf	Q4_K_S	3.86GB
dec10.Q4_K.gguf	Q4_K	4.07GB
dec10.Q4_K_M.gguf	Q4_K_M	4.07GB
dec10.Q4_1.gguf	Q4_1	4.24GB
dec10.Q5_0.gguf	Q5_0	4.65GB
dec10.Q5_K_S.gguf	Q5_K_S	4.65GB
dec10.Q5_K.gguf	Q5_K	4.78GB
dec10.Q5_K_M.gguf	Q5_K_M	4.78GB
dec10.Q5_1.gguf	Q5_1	5.07GB
dec10.Q6_K.gguf	Q6_K	5.53GB
dec10.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language:

en license: cc-by-nc-4.0 tags:
merge datasets:
Intel/orca_dpo_pairs
athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW pipeline_tag: text-generation model-index:
name: dec10 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: 69.11 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 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: 86.46 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 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: 64.98 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 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: 60.42 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 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: 80.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 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: 70.58 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10 name: Open LLM Leaderboard

Slerp Merge of rwitz/go-bruins-v2 and Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

Go Bruins V2 - A Fine-tuned Language Model

Updates

Overview

Go Bruins-V2 is a language model fine-tuned on the rwitz/go-bruins architecture. It's designed to push the boundaries of NLP applications, offering unparalleled performance in generating human-like text.

Model Details

Developer: Ryan Witzman
Base Model: rwitz/go-bruins
Fine-tuning Method: Direct Preference Optimization (DPO)
Training Steps: 642
Language: English
License: MIT

Capabilities

Go Bruins excels in a variety of NLP tasks, including but not limited to:

Text generation
Language understanding
Sentiment analysis

Usage

Warning: This model may output NSFW or illegal content. Use with caution and at your own risk.

For Direct Use:

python

from transformers import pipeline

model_name = "rwitz/go-bruins-v2"
inference_pipeline = pipeline('text-generation', model=model_name)

input_text = "Your input text goes here"
output = inference_pipeline(input_text)

print(output)

Not Recommended For:

Illegal activities
Harassment
Professional advice or crisis situations

Training and Evaluation

Trained on a dataset from athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW, Go Bruins V2 has shown promising improvements over its predecessor, Go Bruins.

Evaluations

Metric	Average	Arc Challenge	Hella Swag	MMLU	Truthful Q&A	Winogrande	GSM8k
Score	??	??.8	??.05	??.75	??.7	??.45	??.67

Note: The original MMLU evaluation has been corrected to include 5-shot data rather than 1-shot data.

Contact

For any inquiries or feedback, reach out to Ryan Witzman on Discord: rwitz_.

Citations

@misc{unacybertron7b,
  title={Cybertron: Uniform Neural Alignment}, 
  author={Xavier Murias},
  year={2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
  howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16}},
}

This model card was created with care by Ryan Witzman. rewrite this model card for new version called go-bruins-v2 that is finetuned on dpo on the original go-bruins model on athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.05
AI2 Reasoning Challenge (25-Shot)	69.11
HellaSwag (10-Shot)	86.46
MMLU (5-Shot)	64.98
TruthfulQA (0-shot)	60.42
Winogrande (5-shot)	80.74
GSM8k (5-shot)	70.58

RichardErkhov/rwitz_-_dec10-gguf