Hugging Face's logo

noneUsername
/
Mistral-Small-24B-Instruct-2501-W8A8

Safetensors
mistral
8-bit precision
compressed-tensors
Model card Files
xet
Community
noneUsername commited on
Commit
70cf80c
·
verified ·
1 Parent(s): b5848ee

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - mistralai/Mistral-Small-24B-Instruct-2501
4
+ ---
5
+ vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
6
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
7
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
8
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.928|± |0.0164|
9
+ | | |strict-match | 5|exact_match|↑ |0.916|± |0.0176|
10
+
11
+ vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
12
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
13
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
14
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.910|± |0.0128|
15
+ | | |strict-match | 5|exact_match|↑ |0.904|± |0.0132|
16
+
17
+ vllm (pretrained=/root/autodl-tmp/Mistral-Small-24B-Instruct-2501,add_bos_token=true,max_model_len=700,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
18
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
19
+ |------------------|------:|------|------|------|---|-----:|---|-----:|
20
+ |mmlu | 2|none | |acc |↑ |0.7977|± |0.0130|
21
+ | - humanities | 2|none | |acc |↑ |0.8205|± |0.0267|
22
+ | - other | 2|none | |acc |↑ |0.8154|± |0.0266|
23
+ | - social sciences| 2|none | |acc |↑ |0.8667|± |0.0247|
24
+ | - stem | 2|none | |acc |↑ |0.7263|± |0.0249|
25
+
26
+
27
+ vllm (pretrained=/root/autodl-tmp/86-512,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
28
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
29
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
30
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.936|± |0.0155|
31
+ | | |strict-match | 5|exact_match|↑ |0.928|± |0.0164|
32
+
33
+ vllm (pretrained=/root/autodl-tmp/86-512,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
34
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
35
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
36
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ | 0.92|± |0.0121|
37
+ | | |strict-match | 5|exact_match|↑ | 0.91|± |0.0128|
38
+
39
+ vllm (pretrained=/root/autodl-tmp/86-512,add_bos_token=true,max_model_len=700,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
40
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
41
+ |------------------|------:|------|------|------|---|-----:|---|-----:|
42
+ |mmlu | 2|none | |acc |↑ |0.7942|± |0.0131|
43
+ | - humanities | 2|none | |acc |↑ |0.8308|± |0.0255|
44
+ | - other | 2|none | |acc |↑ |0.8000|± |0.0275|
45
+ | - social sciences| 2|none | |acc |↑ |0.8556|± |0.0253|
46
+ | - stem | 2|none | |acc |↑ |0.7263|± |0.0252|
47
+
48
+
49
+ vllm (pretrained=/root/autodl-tmp/876-512,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
50
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
51
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
52
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.904|± |0.0187|
53
+ | | |strict-match | 5|exact_match|↑ |0.904|± |0.0187|
54
+
55
+ vllm (pretrained=/root/autodl-tmp/876-512,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
56
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
57
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
58
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.904|± |0.0132|
59
+ | | |strict-match | 5|exact_match|↑ |0.900|± |0.0134|
60
+
61
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
62
+ |------------------|------:|------|------|------|---|-----:|---|-----:|
63
+ |mmlu | 2|none | |acc |↑ |0.7942|± |0.0130|
64
+ | - humanities | 2|none | |acc |↑ |0.8256|± |0.0259|
65
+ | - other | 2|none | |acc |↑ |0.8051|± |0.0266|
66
+ | - social sciences| 2|none | |acc |↑ |0.8556|± |0.0255|
67
+ | - stem | 2|none | |acc |↑ |0.7263|± |0.0248|
68
+
69
+
70
+ vllm (pretrained=/root/autodl-tmp/883-2048,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
71
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
72
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
73
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.904|± |0.0187|
74
+ | | |strict-match | 5|exact_match|↑ |0.904|± |0.0187|
75
+
76
+ vllm (pretrained=/root/autodl-tmp/883-2048,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
77
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
78
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
79
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.900|± |0.0134|
80
+ | | |strict-match | 5|exact_match|↑ |0.898|± |0.0135|
81
+
82
+ vllm (pretrained=/root/autodl-tmp/883-2048,add_bos_token=true,max_model_len=700,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
83
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
84
+ |------------------|------:|------|------|------|---|-----:|---|-----:|
85
+ |mmlu | 2|none | |acc |↑ |0.7930|± |0.0131|
86
+ | - humanities | 2|none | |acc |↑ |0.8256|± |0.0259|
87
+ | - other | 2|none | |acc |↑ |0.7897|± |0.0279|
88
+ | - social sciences| 2|none | |acc |↑ |0.8667|± |0.0246|
89
+ | - stem | 2|none | |acc |↑ |0.7263|± |0.0249|
90
+
91
+
92
+ vllm (pretrained=/root/autodl-tmp/89-1024,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
93
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
94
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
95
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.908|± |0.0183|
96
+ | | |strict-match | 5|exact_match|↑ |0.904|± |0.0187|
97
+
98
+ vllm (pretrained=/root/autodl-tmp/89-1024,add_bos_token=true,max_model_len=2048,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
99
+ |Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
100
+ |-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
101
+ |gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.906|± |0.0131|
102
+ | | |strict-match | 5|exact_match|↑ |0.900|± |0.0134|
103
+
104
+ vllm (pretrained=/root/autodl-tmp/89-1024,add_bos_token=true,max_model_len=700,tensor_parallel_size=2,dtype=bfloat16), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
105
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
106
+ |------------------|------:|------|------|------|---|-----:|---|-----:|
107
+ |mmlu | 2|none | |acc |↑ |0.7906|± |0.0131|
108
+ | - humanities | 2|none | |acc |↑ |0.8205|± |0.0261|
109
+ | - other | 2|none | |acc |↑ |0.7949|± |0.0275|
110
+ | - social sciences| 2|none | |acc |↑ |0.8667|± |0.0246|
111
+ | - stem | 2|none | |acc |↑ |0.7193|± |0.0249|