Update README.md
Browse filestest out metrics metadata
README.md
CHANGED
|
@@ -27,6 +27,43 @@ datasets:
|
|
| 27 |
- nickrosh/Evol-Instruct-Code-80k-v1
|
| 28 |
- open-phi/textbooks
|
| 29 |
- open-phi/programming_books_llama
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
---
|
| 31 |
|
| 32 |
# CrystalChat
|
|
|
|
| 27 |
- nickrosh/Evol-Instruct-Code-80k-v1
|
| 28 |
- open-phi/textbooks
|
| 29 |
- open-phi/programming_books_llama
|
| 30 |
+
|
| 31 |
+
model-index:
|
| 32 |
+
- name: CrystalChat
|
| 33 |
+
results:
|
| 34 |
+
- task:
|
| 35 |
+
type: multiple-choice # Required. Example: automatic-speech-recognition
|
| 36 |
+
dataset:
|
| 37 |
+
type: race # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
|
| 38 |
+
name: RACE # Required. A pretty name for the dataset. Example: Common Voice (French)
|
| 39 |
+
metrics:
|
| 40 |
+
- name: accuracy
|
| 41 |
+
type: accuracy # Required. Example: wer. Use metric id from https://hf.co/metrics
|
| 42 |
+
value: 41.148 # Required. Example: 41.148
|
| 43 |
+
- task:
|
| 44 |
+
type: text-generation # Required. Example: automatic-speech-recognition
|
| 45 |
+
dataset:
|
| 46 |
+
type: openai_humanneval # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
|
| 47 |
+
name: OpenAI HumanEval # Required. A pretty name for the dataset. Example: Common Voice (French)
|
| 48 |
+
metrics:
|
| 49 |
+
- name: pass@1
|
| 50 |
+
type: pass@1 # Required. Example: wer. Use metric id from https://hf.co/metrics
|
| 51 |
+
value: 31.707 # Required. Example: 41.148
|
| 52 |
+
- name: pass@10
|
| 53 |
+
type: pass@10
|
| 54 |
+
value: 65.755
|
| 55 |
+
- task:
|
| 56 |
+
type: text-generation # Required. Example: automatic-speech-recognition
|
| 57 |
+
dataset:
|
| 58 |
+
type: mbpp # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
|
| 59 |
+
name: Mostly Basic Python Problems (mbpp) # Required. A pretty name for the dataset. Example: Common Voice (French)
|
| 60 |
+
metrics:
|
| 61 |
+
- name: pass@1
|
| 62 |
+
type: pass@1 # Required. Example: wer. Use metric id from https://hf.co/metrics
|
| 63 |
+
value: 39.4 # Required. Example: 41.148
|
| 64 |
+
- name: pass@10
|
| 65 |
+
type: pass@10
|
| 66 |
+
value: 59.895
|
| 67 |
---
|
| 68 |
|
| 69 |
# CrystalChat
|