Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 0.0
+      value:  75.61
       verified: false
 ---
 
@@ -38,6 +38,44 @@ Total 153,013 samples.
 - WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
 
 
+
+## HumanEval
+
+| human-eval | pass@1 |
+| --- | --- |
+| humaneval-python | 75.61 |
+
+[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
+
+| Models | pass@1 |
+|------ | ------ |
+| Phind-CodeLlama-34B-v2|  71.95| 
+| WizardCoder-Python-34B-V1.0|  70.73| 
+| Phind-CodeLlama-34B-Python-v1|  70.22| 
+| Phind-CodeLlama-34B-v1|  65.85| 
+| WizardCoder-Python-13B-V1.0|  62.19| 
+| WizardCoder-15B-V1.0|  58.12| 
+| CodeLlama-34B-Python|  53.29| 
+| CodeLlama-34B-Instruct|  50.79| 
+| CodeLlama-13B-Instruct|  50.6| 
+| CodeLlama-34B|  45.11| 
+| CodeLlama-13B-Python|  42.89| 
+| CodeLlama-13B|  35.07| 
+
+
+## lm-evaluation-harness
+
+[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+| Metric | Value |
+| --- | --- |
+| ARC | |
+| HellaSwag | |
+| MMLU | |
+| TruthfulQA |  |
+| Average |  |
+
+
+## Training Arguments
 | | |
 |------ | ------ |
 | lr | 2e-4 |
@@ -73,33 +111,6 @@ A40-48G x 2
 | eeval_samples_per_second |      5.525 |
 | eeval_steps_per_second   |      2.763 |
 
-| Metric | Value |
-| --- | --- |
-| humaneval-python | |
-
-[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
-
-CodeLlama-34B-Python: 53.29
-
-CodeLlama-34B-Instruct: 50.79
-
-CodeLlama-13B-Instruct: 50.6
-
-CodeLlama-34B: 45.11
-
-CodeLlama-13B-Python: 42.89
-
-CodeLlama-13B: 35.07
-
-[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
-| Metric | Value |
-| --- | --- |
-| ARC | |
-| HellaSwag | |
-| MMLU | |
-| TruthfulQA |  |
-| Average |  |
-
 
 # **Code Llama**