Hugging Face's logo

giannisan
/
Mistral-10.7B-Instruct-v0.3-depth-upscaling

Text Generation
Transformers
Safetensors
English
mistral
conversational
text-generation-inference
Model card Files Community
giannisan commited on
Commit
de1839f
·
verified ·
1 Parent(s): b404f5b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -49,11 +49,11 @@ dtype: bfloat16
49
  Eval results:
50
  | Metric | Value |
51
  |----------------------|-------|
52
- | **Avg.** | 57.64 |
53
  | **ARC (25-shot)** | 63.14 |
54
  | **HellaSwag (10-shot)** | 83.29 |
55
  | **MMLU (5-shot)** | 62.31 |
56
- | **TruthfulQA (0-shot)** | 60.61 |
57
  | **Winogrande (5-shot)** | 78.45 |
58
  | **GSM8K (5-shot)** | 36.39 |
59
  Full results [here](https://huggingface.co/datasets/open-llm-leaderboard/details_giannisan__Mistral-10.7B-Instruct-v0.3-depth-upscaling/blob/main/results_2024-05-30T06-01-17.134852.json)
 
49
  Eval results:
50
  | Metric | Value |
51
  |----------------------|-------|
52
+ | **Avg.** | 64.04 |
53
  | **ARC (25-shot)** | 63.14 |
54
  | **HellaSwag (10-shot)** | 83.29 |
55
  | **MMLU (5-shot)** | 62.31 |
56
+ | **TruthfulQA (0-shot)** | 60.65 |
57
  | **Winogrande (5-shot)** | 78.45 |
58
  | **GSM8K (5-shot)** | 36.39 |
59
  Full results [here](https://huggingface.co/datasets/open-llm-leaderboard/details_giannisan__Mistral-10.7B-Instruct-v0.3-depth-upscaling/blob/main/results_2024-05-30T06-01-17.134852.json)