NousResearch
/

Yarn-Llama-2-70b-32k

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

emozilla commited on Nov 17, 2023

Commit

4699e73

•

1 Parent(s): e610773

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -47,10 +47,10 @@ Long context benchmarks:
 | [Yarn-Llama-2-70b-32k](https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k) | 32k | 3.61 | 3.22 | 2.91 | 2.82 | 2.45 | 2.23 |
 Short context benchmarks showing that quality degradation is minimal:
-| Model | Context Window | ARC-c | Hellaswag | MMLU | Truthful QA |
-|-------|---------------:|------:|----------:|-----:|------------:|
-| [Llama-2-70b-hf](meta-llama/Llama-2-70b-hf) | 4k | 67.32 | 87.33 | 69.83 | 44.92 |
-| [Yarn-Llama-2-70b-32k](https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k) | 32k | 67.41 | - | 68.84 | - |
 ## Collaborators

 | [Yarn-Llama-2-70b-32k](https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k) | 32k | 3.61 | 3.22 | 2.91 | 2.82 | 2.45 | 2.23 |
 Short context benchmarks showing that quality degradation is minimal:
+| Model | Context Window | ARC-c | MMLU | Truthful QA |
+|-------|---------------:|------:|-----:|------------:|
+| [Llama-2-70b-hf](meta-llama/Llama-2-70b-hf) | 4k | 67.32 | 69.83 | 44.92 |
+| [Yarn-Llama-2-70b-32k](https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k) | 32k | 67.41 | 68.84 | 46.14 |
 ## Collaborators