Commit
•
67b586a
1
Parent(s):
0b6fc3c
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
|
@@ -1,6 +1,101 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
Converted using [this script](https://huggingface.co/Downtown-Case/internlm_internlm2_5-20b-llamafied-hacked-rope/blob/main/convert_weights_internlm.py), then edited the tokenizer manually to (hopefully) match the behaviour of the original. Matches the original model at temperature=0 after some quick tests, but not extensively verified.
|
|
@@ -154,3 +249,17 @@ print(output)
|
|
| 154 |
primaryClass={cs.CL}
|
| 155 |
}
|
| 156 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
pipeline_tag: text-generation
|
| 4 |
+
model-index:
|
| 5 |
+
- name: internlm2_5-20b-llamafied
|
| 6 |
+
results:
|
| 7 |
+
- task:
|
| 8 |
+
type: text-generation
|
| 9 |
+
name: Text Generation
|
| 10 |
+
dataset:
|
| 11 |
+
name: IFEval (0-Shot)
|
| 12 |
+
type: HuggingFaceH4/ifeval
|
| 13 |
+
args:
|
| 14 |
+
num_few_shot: 0
|
| 15 |
+
metrics:
|
| 16 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 17 |
+
value: 34.1
|
| 18 |
+
name: strict accuracy
|
| 19 |
+
source:
|
| 20 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 21 |
+
name: Open LLM Leaderboard
|
| 22 |
+
- task:
|
| 23 |
+
type: text-generation
|
| 24 |
+
name: Text Generation
|
| 25 |
+
dataset:
|
| 26 |
+
name: BBH (3-Shot)
|
| 27 |
+
type: BBH
|
| 28 |
+
args:
|
| 29 |
+
num_few_shot: 3
|
| 30 |
+
metrics:
|
| 31 |
+
- type: acc_norm
|
| 32 |
+
value: 63.47
|
| 33 |
+
name: normalized accuracy
|
| 34 |
+
source:
|
| 35 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 36 |
+
name: Open LLM Leaderboard
|
| 37 |
+
- task:
|
| 38 |
+
type: text-generation
|
| 39 |
+
name: Text Generation
|
| 40 |
+
dataset:
|
| 41 |
+
name: MATH Lvl 5 (4-Shot)
|
| 42 |
+
type: hendrycks/competition_math
|
| 43 |
+
args:
|
| 44 |
+
num_few_shot: 4
|
| 45 |
+
metrics:
|
| 46 |
+
- type: exact_match
|
| 47 |
+
value: 17.07
|
| 48 |
+
name: exact match
|
| 49 |
+
source:
|
| 50 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 51 |
+
name: Open LLM Leaderboard
|
| 52 |
+
- task:
|
| 53 |
+
type: text-generation
|
| 54 |
+
name: Text Generation
|
| 55 |
+
dataset:
|
| 56 |
+
name: GPQA (0-shot)
|
| 57 |
+
type: Idavidrein/gpqa
|
| 58 |
+
args:
|
| 59 |
+
num_few_shot: 0
|
| 60 |
+
metrics:
|
| 61 |
+
- type: acc_norm
|
| 62 |
+
value: 11.74
|
| 63 |
+
name: acc_norm
|
| 64 |
+
source:
|
| 65 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 66 |
+
name: Open LLM Leaderboard
|
| 67 |
+
- task:
|
| 68 |
+
type: text-generation
|
| 69 |
+
name: Text Generation
|
| 70 |
+
dataset:
|
| 71 |
+
name: MuSR (0-shot)
|
| 72 |
+
type: TAUR-Lab/MuSR
|
| 73 |
+
args:
|
| 74 |
+
num_few_shot: 0
|
| 75 |
+
metrics:
|
| 76 |
+
- type: acc_norm
|
| 77 |
+
value: 14.94
|
| 78 |
+
name: acc_norm
|
| 79 |
+
source:
|
| 80 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 81 |
+
name: Open LLM Leaderboard
|
| 82 |
+
- task:
|
| 83 |
+
type: text-generation
|
| 84 |
+
name: Text Generation
|
| 85 |
+
dataset:
|
| 86 |
+
name: MMLU-PRO (5-shot)
|
| 87 |
+
type: TIGER-Lab/MMLU-Pro
|
| 88 |
+
config: main
|
| 89 |
+
split: test
|
| 90 |
+
args:
|
| 91 |
+
num_few_shot: 5
|
| 92 |
+
metrics:
|
| 93 |
+
- type: acc
|
| 94 |
+
value: 33.9
|
| 95 |
+
name: accuracy
|
| 96 |
+
source:
|
| 97 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=IntervitensInc/internlm2_5-20b-llamafied
|
| 98 |
+
name: Open LLM Leaderboard
|
| 99 |
---
|
| 100 |
|
| 101 |
Converted using [this script](https://huggingface.co/Downtown-Case/internlm_internlm2_5-20b-llamafied-hacked-rope/blob/main/convert_weights_internlm.py), then edited the tokenizer manually to (hopefully) match the behaviour of the original. Matches the original model at temperature=0 after some quick tests, but not extensively verified.
|
|
|
|
| 249 |
primaryClass={cs.CL}
|
| 250 |
}
|
| 251 |
```
|
| 252 |
+
|
| 253 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 254 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_IntervitensInc__internlm2_5-20b-llamafied)
|
| 255 |
+
|
| 256 |
+
| Metric |Value|
|
| 257 |
+
|-------------------|----:|
|
| 258 |
+
|Avg. |29.20|
|
| 259 |
+
|IFEval (0-Shot) |34.10|
|
| 260 |
+
|BBH (3-Shot) |63.47|
|
| 261 |
+
|MATH Lvl 5 (4-Shot)|17.07|
|
| 262 |
+
|GPQA (0-shot) |11.74|
|
| 263 |
+
|MuSR (0-shot) |14.94|
|
| 264 |
+
|MMLU-PRO (5-shot) |33.90|
|
| 265 |
+
|