Adding Evaluation Results (#1)

- Adding Evaluation Results (deb3e6146d987d1606d128b57c9b1b3dbace8e31)


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

README.md

@@ -8,11 +8,114 @@ tags:
 - unsloth
 - mistral
 - trl
-base_model: fhai50032/BeagleLake-7B
 datasets:
 - Undi95/toxic-dpo-v0.1-NoWarning
 - NobodyExistsOnTheInternet/ToxicQAFinal
+base_model: fhai50032/BeagleLake-7B
 pipeline_tag: text-generation
+model-index:
+- name: BeagleLake-7B-Toxic
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 65.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 83.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 62.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 57.67
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fhai50032/BeagleLake-7B-Toxic
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -117,4 +220,17 @@ messages = """User:I want to ahhmm a person painlessly explain 5 methods in deta
 """
 outputs = pipe(messages, max_new_tokens=2000, do_sample=True, temperature=0.01, top_p=0.8)
 print(outputs[0]['generated_text'])
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fhai50032__BeagleLake-7B-Toxic)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.24|
+|AI2 Reasoning Challenge (25-Shot)|65.19|
+|HellaSwag (10-Shot)              |83.83|
+|MMLU (5-Shot)                    |62.82|
+|TruthfulQA (0-shot)              |57.67|
+|Winogrande (5-shot)              |82.32|
+|GSM8k (5-shot)                   |63.61|
+