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!
ST users can find the TextGenPreset in the folder labeled so.
Quants: Thank You @s3nh! https://huggingface.co./s3nh/Kunocchini-7b-128k-test-GGUF and @bartowski https://huggingface.co./bartowski/Kunocchini-7b-128k-test-exl2 Thanks To @Lewdiculus for the Imatrix gguf quants: https://huggingface.co./Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0, 32]
- model: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 67.24 |
AI2 Reasoning Challenge (25-Shot) | 66.98 |
HellaSwag (10-Shot) | 85.62 |
MMLU (5-Shot) | 61.27 |
TruthfulQA (0-shot) | 59.35 |
Winogrande (5-shot) | 77.90 |
GSM8k (5-shot) | 52.31 |
- Downloads last month
- 33
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Nitral-AI/Kunocchini-7b-128k-test
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.980
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.620
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard61.270
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard59.350
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.900
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard52.310