Hugging Face's logo

TIGER-Lab
/
MAmmoTH2-8x7B

Text Generation
Transformers
Safetensors
English
mixtral
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
aaabiao commited on
Commit
ffe24df
·
verified ·
1 Parent(s): e9b3cf5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -20
README.md CHANGED
@@ -29,26 +29,18 @@ The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-
29
  The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
30
 
31
 
32
- | **Model** | **Decoding** | **GSM** | **MATH** | **AQuA** | **NumG** | **SVA** | **Mat** | **Sim** | **SAT** | **MMLU** | **AVG** |
33
- |-----------------------|--------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|----------|
34
- | **MAmmoTH2-7B** | CoT | 50.5 | 10.4 | 43.7 | 44.0 | 47.3 | 9.2 | 18.9 | 32.7 | 39.9 | 33.0 |
35
- | | PoT | 51.6 | 28.7 | 43.3 | 52.3 | 65.1 | 41.9 | 48.2 | 39.1 | 44.6 | 46.1 |
36
- | | **Hybrid** | **53.6** | **31.5** | **44.5** | **61.2** | **67.7** | **46.3** | **41.2** | **42.7** | **42.6** | **47.9** |
37
- | **MAmmoTH2-8B** | CoT | 22.4 | 7.9 | 36.2 | 36.0 | 37.0 | 8.2 | 7.2 | 32.7 | 34.6 | 24.7 |
38
- | | PoT | 58.8 | 32.1 | 47.2 | 57.1 | 71.1 | 53.9 | 44.6 | 40.0 | 47.8 | 50.3 |
39
- | | **Hybrid** | **59.4** | **33.4** | **47.2** | **66.4** | **71.4** | **55.4** | **45.9** | **40.5** | **48.3** | **52.0** |
40
- | **MAmmoTH2-8x7B** | CoT | 56.3 | 12.9 | 45.3 | 45.6 | 53.8 | 11.7 | 22.4 | 43.6 | 42.3 | 37.1 |
41
- | | PoT | 61.3 | 32.6 | 48.8 | 59.6 | 72.2 | 48.5 | 40.3 | 46.8 | 45.4 | 50.6 |
42
- | | **Hybrid** | **62.0** | **34.2** | **51.6** | **68.7** | **72.4** | **49.2** | **43.2** | **46.8** | **47.6** | **52.9** |
43
- | **MAmmoTH2-7B-Plus** | CoT | 50.5 | 10.4 | 43.7 | 44.0 | 47.3 | 9.2 | 18.9 | 32.7 | 39.9 | 33.0 |
44
- | | PoT | 51.6 | 28.7 | 43.3 | 52.3 | 65.1 | 41.9 | 48.2 | 39.1 | 44.6 | 46.1 |
45
- | | **Hybrid** | **53.6** | **31.5** | **44.5** | **61.2** | **67.7** | **46.3** | **41.2** | **42.7** | **42.6** | **47.9** |
46
- | **MAmmoTH2-8B-Plus** | CoT | 22.4 | 7.9 | 36.2 | 36.0 | 37.0 | 8.2 | 7.2 | 32.7 | 34.6 | 24.7 |
47
- | | PoT | 58.8 | 32.1 | 47.2 | 57.1 | 71.1 | 53.9 | 44.6 | 40.0 | 47.8 | 50.3 |
48
- | | **Hybrid** | **59.4** | **33.4** | **47.2** | **66.4** | **71.4** | **55.4** | **45.9** | **40.5** | **48.3** | **52.0** |
49
- | **MAmmoTH2-8x7B-Plus** | CoT | 56.3 | 12.9 | 45.3 | 45.6 | 53.8 | 11.7 | 22.4 | 43.6 | 42.3 | 37.1 |
50
- | | PoT | 61.3 | 32.6 | 48.8 | 59.6 | 72.2 | 48.5 | 40.3 | 46.8 | 45.4 | 50.6 |
51
- | | **Hybrid** | **62.0** | **34.2** | **51.6** | **68.7** | **72.4** | **49.2** | **43.2** | **46.8** | **47.6** | **52.9** |
52
 
53
 
54
 
 
29
  The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
30
 
31
 
32
+ Sure, here's the information presented in the format you provided:
33
+
34
+ Certainly, here's the updated table with the model names in bold:
35
+
36
+ | **Model** | **Decoding** | **GSM** | **MATH** | **GPQA** | **MMLU-ST** | **BBH** | **ARC-C** | **Avg** |
37
+ |------------------------|--------------|---------|----------|----------|-------------|---------|-----------|---------|
38
+ | **MAmmoTH2-7B** | 26.7 | 34.2 | 67.4 | 34.8 | 60.6 | 60.0 | 81.8 | 52.2 |
39
+ | **MAmmoTH2-8B** | 29.7 | 33.4 | 67.9 | 38.4 | 61.0 | 60.8 | 81.0 | 53.1 |
40
+ | **MAmmoTH2-8x7B** | 32.2 | 39.0 | 75.4 | 36.8 | 67.4 | 71.1 | 87.5 | 58.9 |
41
+ | **MAmmoTH2-7B-Plus** | 29.2 | 45.0 | 84.7 | 36.8 | 64.5 | 63.1 | 83.0 | 58.0 |
42
+ | **MAmmoTH2-8B-Plus** | 32.5 | 42.8 | 84.1 | 37.3 | 65.7 | 67.8 | 83.4 | 59.1 |
43
+ | **MAmmoTH2-8x7B-Plus** | 34.1 | 47.0 | 86.4 | 37.8 | 72.4 | 74.1 | 88.4 | 62.9 |
 
 
 
 
 
 
 
 
44
 
45
 
46