Nitral-AI/Kunocchini-1.2-7b-longtext-broken

NOTES: This model seems to be overtly confident leading to hallucinations, normalization has seemed to also break the long context chaining. I do not recommend this model.

Thanks to @Epiculous for the dope model/ help with llm backends and support overall.

Id like to also thank @kalomaze for the dope sampler additions to ST.

@SanjiWatsuki Thank you very much for the help, and the model!

Quants Here: Thanks to @Lewdiculus https://huggingface.co/Lewdiculous/Kunocchini-1.2-7b-longtext-GGUF-Imatrix

This model was merged using the DARE TIES.

Models Merged

The following models were included in the merge:

• NousResearch/Yarn-Mistral-7b-128k + Test157t/Kunocchini-1.1-7b

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Test157t/Kunocchini-1.1-7b
parameters:
  normalize: true
models:
  - model: NousResearch/Yarn-Mistral-7b-128k
    parameters:
      weight: 1
  - model: Test157t/Kunocchini-1.1-7b
    parameters:
      weight: 1
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.57
AI2 Reasoning Challenge (25-Shot)	59.90
HellaSwag (10-Shot)	82.51
MMLU (5-Shot)	63.05
TruthfulQA (0-shot)	41.72
Winogrande (5-shot)	77.35
GSM8k (5-shot)	32.90