Update README.md
Browse files
README.md
CHANGED
|
@@ -127,15 +127,12 @@ model-index:
|
|
| 127 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
|
| 128 |
name: Open LLM Leaderboard
|
| 129 |
---
|
|
|
|
| 130 |
Please note, the low IFEVAL results is due to this model always reasoning, instruction following is limited, which caused it to have very low ifeval results, this should not matter for most use cases.
|
| 131 |
gguf/final version: https://huggingface.co/Pinkstack/PARM-V2-phi-4-16k-CoT-o1-gguf
|
| 132 |
|
| 133 |
This model can be merged with phi-4 based LLMs!
|
| 134 |
|
| 135 |
-
other gguf version: mradermacher/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
[Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)
|
| 140 |
[superthoughts 14B openllm detailed results](https://huggingface.co/datasets/open-llm-leaderboard/Pinkstack__SuperThoughts-CoT-14B-16k-o1-QwQ-details)
|
| 141 |
Phi-4 that has been tuned to be more advanced at reasoning.
|
|
|
|
| 127 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
|
| 128 |
name: Open LLM Leaderboard
|
| 129 |
---
|
| 130 |
+
Renamed to parm-2
|
| 131 |
Please note, the low IFEVAL results is due to this model always reasoning, instruction following is limited, which caused it to have very low ifeval results, this should not matter for most use cases.
|
| 132 |
gguf/final version: https://huggingface.co/Pinkstack/PARM-V2-phi-4-16k-CoT-o1-gguf
|
| 133 |
|
| 134 |
This model can be merged with phi-4 based LLMs!
|
| 135 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
[Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)
|
| 137 |
[superthoughts 14B openllm detailed results](https://huggingface.co/datasets/open-llm-leaderboard/Pinkstack__SuperThoughts-CoT-14B-16k-o1-QwQ-details)
|
| 138 |
Phi-4 that has been tuned to be more advanced at reasoning.
|