Commit
•
29d752f
1
Parent(s):
d09c2a1
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,36 @@ I ran the tests for 2 runs just to try to lower variance. These are all using te
|
|
| 29 |
* 2e-5 is on the edge since weightwacher shows the embed as slightly overtrained for 2e-5, but NEFTune version is not
|
| 30 |
* 8e-6 performs the best, and 5e-6 also performed slightly better than 2e-5
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 34 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
| 29 |
* 2e-5 is on the edge since weightwacher shows the embed as slightly overtrained for 2e-5, but NEFTune version is not
|
| 30 |
* 8e-6 performs the best, and 5e-6 also performed slightly better than 2e-5
|
| 31 |
|
| 32 |
+
For a comparison of where it sits vs other models:
|
| 33 |
+
|
| 34 |
+
| Model | Average | ELYZA-tasks-100 | MT-Bench | Rakuda | Tengu-Bench |
|
| 35 |
+
|----------------------------------------|---------|-----------------|----------|--------|-------------|
|
| 36 |
+
| gpt-4-turbo-2024-04-09 | 8.75 | 8.78 | 8.74 | 9.18 | 8.31 |
|
| 37 |
+
| gpt-4o-2024-05-13 | 8.72 | 8.88 | 8.69 | 9.15 | 8.16 |
|
| 38 |
+
| gemini-1.5-pro | 8.58 | 8.58 | 8.93 | 9.20 | 7.61 |
|
| 39 |
+
| claude-3-opus-20240229 | 8.55 | 8.64 | 8.58 | 8.75 | 8.23 |
|
| 40 |
+
| CohereForAI/c4ai-command-r-plus | 7.69 | 7.50 | 7.43 | 9.05 | 6.79 |
|
| 41 |
+
| **shisa-ai/shisa-v1-llama3-70b** | **7.30**| **7.34** | **7.67** | **8.15** | **6.04** |
|
| 42 |
+
| gpt-3.5-turbo-0125 | 7.17 | 7.24 | 6.98 | 7.64 | 6.82 |
|
| 43 |
+
| **shisa-ai/shisa-v1-llama3-70b.2e5** | **7.17**| **7.16** | **7.45** | **7.98** | **6.09** |
|
| 44 |
+
| karakuri-ai/karakuri-lm-8x7b-chat-v0.1 | 7.00 | 7.18 | 6.30 | 7.98 | 6.55 |
|
| 45 |
+
| karakuri-ai/karakuri-lm-70b-chat-v0.1 | 6.84 | 6.86 | 6.43 | 7.85 | 6.23 |
|
| 46 |
+
| lightblue/ao-karasu-72B | 6.81 | 7.19 | 6.54 | 7.25 | 6.27 |
|
| 47 |
+
| **shisa-ai/shisa-v1-llama3-8b** | **6.59**| **6.67** | **6.95** | **7.05**| **5.68** |
|
| 48 |
+
| **shisa-ai/shisa-swallowmx-13a47b-v1** | **6.17**| **6.48** | **6.07** | **7.11**| **5.03** |
|
| 49 |
+
| lightblue/suzume-llama-3-8B-japanese | 5.96 | 6.68 | 4.96 | 6.68 | 5.53 |
|
| 50 |
+
| augmxnt/shisa-gamma-7b-v1 | 5.82 | 5.96 | 5.02 | 6.85 | 5.47 |
|
| 51 |
+
| **shisa-ai/shisa-v1-phi3-14b** | **5.77**| **6.28** | **5.26** | **6.55**| **5.01** |
|
| 52 |
+
| **shisa-ai/shisa-v1-gemma-8b** | **5.64**| **6.50** | **5.42** | **5.10**| **5.55** |
|
| 53 |
+
| Rakuten/RakutenAI-7B-chat | 5.58 | 5.92 | 4.60 | 6.58 | 5.24 |
|
| 54 |
+
| lightblue/qarasu-14B-chat-plus-unleashed | 5.20 | 5.58 | 4.74 | 5.46 | 5.01 |
|
| 55 |
+
| **shisa-ai/shisa-v1-mistral0.3-7b** | **5.11**| **5.64** | **6.10** | **3.83**|**4.86** |
|
| 56 |
+
| cyberagent/calm2-7b-chat | 4.76 | 4.90 | 3.58 | 5.75 | 4.81 |
|
| 57 |
+
| mistralai/Mistral-7B-Instruct-v0.2 | 4.69 | 5.78 | 4.65 | 3.80 | 4.53 |
|
| 58 |
+
| **shisa-ai/shisa-v1-yi1.5-9b** | **4.63**| **5.98** | **4.28** | **3.26**|**5.00** |
|
| 59 |
+
| augmxnt/shisa-7b-v1 | 4.50 | 4.63 | 3.95 | 4.89 | 4.53 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
|
| 63 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 64 |
should probably proofread and complete it, then remove this comment. -->
|