Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,8 @@ model-index:
|
|
| 22 |
value: 34.45
|
| 23 |
name: strict accuracy
|
| 24 |
source:
|
| 25 |
-
url:
|
|
|
|
| 26 |
name: Open LLM Leaderboard
|
| 27 |
- task:
|
| 28 |
type: text-generation
|
|
@@ -37,7 +38,8 @@ model-index:
|
|
| 37 |
value: 20.78
|
| 38 |
name: normalized accuracy
|
| 39 |
source:
|
| 40 |
-
url:
|
|
|
|
| 41 |
name: Open LLM Leaderboard
|
| 42 |
- task:
|
| 43 |
type: text-generation
|
|
@@ -52,7 +54,8 @@ model-index:
|
|
| 52 |
value: 29.68
|
| 53 |
name: exact match
|
| 54 |
source:
|
| 55 |
-
url:
|
|
|
|
| 56 |
name: Open LLM Leaderboard
|
| 57 |
- task:
|
| 58 |
type: text-generation
|
|
@@ -67,7 +70,8 @@ model-index:
|
|
| 67 |
value: 8.5
|
| 68 |
name: acc_norm
|
| 69 |
source:
|
| 70 |
-
url:
|
|
|
|
| 71 |
name: Open LLM Leaderboard
|
| 72 |
- task:
|
| 73 |
type: text-generation
|
|
@@ -82,7 +86,8 @@ model-index:
|
|
| 82 |
value: 8.18
|
| 83 |
name: acc_norm
|
| 84 |
source:
|
| 85 |
-
url:
|
|
|
|
| 86 |
name: Open LLM Leaderboard
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
|
@@ -99,14 +104,19 @@ model-index:
|
|
| 99 |
value: 21.01
|
| 100 |
name: accuracy
|
| 101 |
source:
|
| 102 |
-
url:
|
|
|
|
| 103 |
name: Open LLM Leaderboard
|
|
|
|
| 104 |
---
|
| 105 |
-
#
|
| 106 |
|
| 107 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 108 |
|
| 109 |
## Merge Details
|
|
|
|
|
|
|
|
|
|
| 110 |
### Merge Method
|
| 111 |
|
| 112 |
This model was merged using the Passthrough merge method using [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) + [bunnycore/Qwen-2.5-7b-rp-lora](https://huggingface.co/bunnycore/Qwen-2.5-7b-rp-lora) as a base.
|
|
@@ -140,5 +150,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 140 |
|MATH Lvl 5 (4-Shot)|29.68|
|
| 141 |
|GPQA (0-shot) | 8.50|
|
| 142 |
|MuSR (0-shot) | 8.18|
|
| 143 |
-
|MMLU-PRO (5-shot) |21.01|
|
| 144 |
-
|
|
|
|
| 22 |
value: 34.45
|
| 23 |
name: strict accuracy
|
| 24 |
source:
|
| 25 |
+
url: >-
|
| 26 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 27 |
name: Open LLM Leaderboard
|
| 28 |
- task:
|
| 29 |
type: text-generation
|
|
|
|
| 38 |
value: 20.78
|
| 39 |
name: normalized accuracy
|
| 40 |
source:
|
| 41 |
+
url: >-
|
| 42 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 43 |
name: Open LLM Leaderboard
|
| 44 |
- task:
|
| 45 |
type: text-generation
|
|
|
|
| 54 |
value: 29.68
|
| 55 |
name: exact match
|
| 56 |
source:
|
| 57 |
+
url: >-
|
| 58 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 59 |
name: Open LLM Leaderboard
|
| 60 |
- task:
|
| 61 |
type: text-generation
|
|
|
|
| 70 |
value: 8.5
|
| 71 |
name: acc_norm
|
| 72 |
source:
|
| 73 |
+
url: >-
|
| 74 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 75 |
name: Open LLM Leaderboard
|
| 76 |
- task:
|
| 77 |
type: text-generation
|
|
|
|
| 86 |
value: 8.18
|
| 87 |
name: acc_norm
|
| 88 |
source:
|
| 89 |
+
url: >-
|
| 90 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 91 |
name: Open LLM Leaderboard
|
| 92 |
- task:
|
| 93 |
type: text-generation
|
|
|
|
| 104 |
value: 21.01
|
| 105 |
name: accuracy
|
| 106 |
source:
|
| 107 |
+
url: >-
|
| 108 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/DS-R1-Distill-Q2.5-7B-RP
|
| 109 |
name: Open LLM Leaderboard
|
| 110 |
+
license: apache-2.0
|
| 111 |
---
|
| 112 |
+
# Merge
|
| 113 |
|
| 114 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 115 |
|
| 116 |
## Merge Details
|
| 117 |
+
|
| 118 |
+
Deepseek Distilled with some Roleplaying.
|
| 119 |
+
|
| 120 |
### Merge Method
|
| 121 |
|
| 122 |
This model was merged using the Passthrough merge method using [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) + [bunnycore/Qwen-2.5-7b-rp-lora](https://huggingface.co/bunnycore/Qwen-2.5-7b-rp-lora) as a base.
|
|
|
|
| 150 |
|MATH Lvl 5 (4-Shot)|29.68|
|
| 151 |
|GPQA (0-shot) | 8.50|
|
| 152 |
|MuSR (0-shot) | 8.18|
|
| 153 |
+
|MMLU-PRO (5-shot) |21.01|
|
|
|