Update README.md
Browse files
README.md
CHANGED
|
@@ -29,11 +29,19 @@ model = AutoModelForCausalLM.from_pretrained("NousResearch/Yarn-Mistral-7b-64k",
|
|
| 29 |
|
| 30 |
## Benchmarks
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
| Model | Context Window | ARC-c | Hellaswag | MMLU | Truthful QA |
|
| 33 |
|-------|---------------:|------:|----------:|-----:|------------:|
|
| 34 |
-
| [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
|
| 35 |
-
| [Yarn-Mistral-7b-64k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k) |
|
| 36 |
-
| [Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) |
|
| 37 |
|
| 38 |
## Collaborators
|
| 39 |
|
|
|
|
| 29 |
|
| 30 |
## Benchmarks
|
| 31 |
|
| 32 |
+
Long context benchmarks:
|
| 33 |
+
| Model | Context Window | 8k PPL | 16k PPL | 32k PPL | 64k PPL | 128k PPL |
|
| 34 |
+
|-------|---------------:|------:|----------:|-----:|-----:|------------:|
|
| 35 |
+
| [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 8k | 2.96 | - | - | - | - |
|
| 36 |
+
| [Yarn-Mistral-7b-64k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k) | 64k | 3.04 | 2.65 | 2.44 | 2.20 | - |
|
| 37 |
+
| [Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) | 128k | 3.08 | 2.68 | 2.47 | 2.24 | 2.19 |
|
| 38 |
+
|
| 39 |
+
Short context benchmarks showing that quality degradation is minimal:
|
| 40 |
| Model | Context Window | ARC-c | Hellaswag | MMLU | Truthful QA |
|
| 41 |
|-------|---------------:|------:|----------:|-----:|------------:|
|
| 42 |
+
| [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 8k | 59.98 | 83.31 | 64.16 | 42.15 |
|
| 43 |
+
| [Yarn-Mistral-7b-64k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k) | 64k | 59.38 | 81.21 | 61.32 | 42.50 |
|
| 44 |
+
| [Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) | 128k | 58.87 | 80.58 | 60.64 | 42.46 |
|
| 45 |
|
| 46 |
## Collaborators
|
| 47 |
|