RossAscends/Paradigm_7B_6bpw_exl2

Paradigm

This is a 8bpw exl2 quant of the Paradigm 7B model. ChatML or Alpaca instruct sequences both work.

---

An incredibly effective and intelligent RP model designed to be the best bot you've ever used. I hope you like it!

GGUF available here: https://huggingface.co/Lewdiculous/Paradigm_7B-GGUF-IQ-Imatrix

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.47
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	88.66
MMLU (5-Shot)	64.02
TruthfulQA (0-shot)	75.19
Winogrande (5-shot)	84.53
GSM8k (5-shot)	66.79

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: ChaoticNeutrals/Eris_Remix_7B
parameters:
  normalize: true
models:
  - model: ChaoticNeutrals/Eris_Remix_7B
    parameters:
      weight: 1
  - model: ResplendentAI/Datura_7B
    parameters:
      weight: 1
  - model: liminerity/Multiverse-Experiment-slerp-7b+jeiku/Alpaca_NSFW_Shuffled_Mistral
    parameters:
      weight: 0.33
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.47
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	88.66
MMLU (5-Shot)	64.02
TruthfulQA (0-shot)	75.19
Winogrande (5-shot)	84.53
GSM8k (5-shot)	66.79