Hugging Face's logo

uukuguy
/
speechless-coding-7b-16k-tora

Text Generation
Transformers
PyTorch
English
llama
llama-2
code
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
uukuguy commited on
Commit
940010a
•
1 Parent(s): 59aa8ed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -10
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: pass@1
26
  type: pass@1
27
- value: 54.27
28
  verified: false
29
  ---
30
 
@@ -43,11 +43,13 @@ Total 177,333 samples 316 MB
43
  - TokenBender/python_eval_instruct_51k: “python” in output .39,596 samples
44
 
45
 
 
 
46
  ## HumanEval
47
 
48
  | Metric | Value |
49
  | --- | --- |
50
- | humaneval-python | 54.27 |
51
 
52
  [Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
53
 
@@ -67,14 +69,14 @@ CodeLlama-13B: 35.07
67
 
68
  | Metric | Value |
69
  | --- | --- |
70
- | python | 59.63 |
71
- | java | 32.28 |
72
- | javascript | 46.58 |
73
- | cpp | 37.83 |
74
- | rust | 28.21 |
75
- | go | 27.27 |
76
- | sh | 13.29 |
77
- | julia | 34.59 |
78
  | typescript | 47.80 |
79
 
80
  ## LMEval
 
24
  metrics:
25
  - name: pass@1
26
  type: pass@1
27
+ value: 52.439
28
  verified: false
29
  ---
30
 
 
43
  - TokenBender/python_eval_instruct_51k: “python” in output .39,596 samples
44
 
45
 
46
+ 50 samples/T=0.2/MaxTokens=512/Top_P=0.95
47
+
48
  ## HumanEval
49
 
50
  | Metric | Value |
51
  | --- | --- |
52
+ | humaneval-python | 52.44 |
53
 
54
  [Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
55
 
 
69
 
70
  | Metric | Value |
71
  | --- | --- |
72
+ | python | 55.96 |
73
+ | java | 37.84 |
74
+ | javascript | 46.93 |
75
+ | cpp | 37.48 |
76
+ | rust | 29.01 |
77
+ | go | 28.99 |
78
+ | sh | 12.11 |
79
+ | julia | 31.47 |
80
  | typescript | 47.80 |
81
 
82
  ## LMEval