migtissera leaderboard-pr-bot commited on
Commit
cdb864f
1 Parent(s): 5f20b9d

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (9621f0b8d46fe95827b3fd1fa7fe82821eec4165)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: other
3
- base_model: mistralai/Codestral-22B-v0.1
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: home/ubuntu/trinity-codestral-1
8
  results: []
@@ -80,4 +80,17 @@ while True:
80
  answer = generate_text(llm_prompt)
81
  print(answer)
82
  conversation = f"{llm_prompt}{answer}<|im_end|>\n<|im_start|>user\n"
83
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: mistralai/Codestral-22B-v0.1
6
  model-index:
7
  - name: home/ubuntu/trinity-codestral-1
8
  results: []
 
80
  answer = generate_text(llm_prompt)
81
  print(answer)
82
  conversation = f"{llm_prompt}{answer}<|im_end|>\n<|im_start|>user\n"
83
+ ```
84
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
85
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_migtissera__Trinity-2-Codestral-22B)
86
+
87
+ | Metric |Value|
88
+ |-------------------|----:|
89
+ |Avg. |21.82|
90
+ |IFEval (0-Shot) |42.02|
91
+ |BBH (3-Shot) |36.41|
92
+ |MATH Lvl 5 (4-Shot)| 8.61|
93
+ |GPQA (0-shot) | 8.61|
94
+ |MuSR (0-shot) | 9.61|
95
+ |MMLU-PRO (5-shot) |25.64|
96
+