Hugging Face's logo

xDAN-AI
/
xDAN-L1-Chat-RL-v1

Text Generation
Transformers
Safetensors
English
mistral
xDAN-AI
OpenOrca
DPO
Self-Think
text-generation-inference
Inference Endpoints
Model card Files Community
3
xDAN2099 commited on
Commit
38ad419
·
1 Parent(s): f31d01c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -33
README.md CHANGED
@@ -37,43 +37,43 @@ tags:
37
 
38
 
39
  ########## First turn ##########
40
- | model | turn | score |
41
- |--------------------|------|----------|
42
- | gpt-4 | 1 | 8.95625 |
43
- | xDAN-L1-Chat-RL-v1 | 1 | 8.87500 |
44
- | xDAN-L2-Chat-RL-v2 | 1 | 8.78750 |
45
- | claude-v1 | 1 | 8.15000 |
46
- | gpt-3.5-turbo | 1 | 8.07500 |
47
- | vicuna-33b-v1.3 | 1 | 7.45625 |
48
- | wizardlm-30b | 1 | 7.13125 |
49
- | oasst-sft-7-llama-30b | 1 | 7.10625 |
50
- | Llama-2-70b-chat | 1 | 6.98750 |
51
 
52
- ########## Second turn ##########
53
- | model | turn | score |
54
- |--------------------|------|-----------|
55
- | gpt-4 | 2 | 9.025000 |
56
- | xDAN-L2-Chat-RL-v2 | 1 | 8.087500 |
57
- | xDAN-L1-Chat-RL-v1 | 2 | 7.825000 |
58
- | gpt-3.5-turbo | 2 | 7.812500 |
59
- | claude-v1 | 2 | 7.650000 |
60
- | wizardlm-30b | 2 | 6.887500 |
61
- | vicuna-33b-v1.3 | 2 | 6.787500 |
62
- | Llama-2-70b-chat | 2 | 6.725000 |
63
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
  ########## Average turn##########
66
- | model | score |
67
- |--------------------|-----------|
68
- | gpt-4 | 8.990625 |
69
- | xDAN-L2-Chat-RL-v2 | 8.437500 |
70
- | xDAN-L1-Chat-RL-v1 | 8.350000 |
71
- | gpt-3.5-turbo | 7.943750 |
72
- | claude-instant-v1 | 7.905660 |
73
- | claude-v1 | 7.900000 |
74
- | vicuna-33b-v1.3 | 7.121875 |
75
- | wizardlm-30b | 7.009375 |
76
- | Llama-2-70b-chat | 6.856250 |
77
 
78
 
79
 
 
37
 
38
 
39
  ########## First turn ##########
40
+ | model | turn | score | size
41
+ |--------------------|------|----------|--------
42
+ | gpt-4 | 1 | 8.95625 | -
43
+ | xDAN-L1-Chat-RL-v1 | 1 | 8.87500 | 7b
44
+ | xDAN-L2-Chat-RL-v2 | 1 | 8.78750 | 30b
45
+ | claude-v1 | 1 | 8.15000 | -
46
+ | gpt-3.5-turbo | 1 | 8.07500 | 20b
47
+ | vicuna-33b-v1.3 | 1 | 7.45625 | 33b
48
+ | wizardlm-30b | 1 | 7.13125 | 30b
49
+ | oasst-sft-7-llama-30b | 1 | 7.10625 | 30b
50
+ | Llama-2-70b-chat | 1 | 6.98750 | 70b
51
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
+ ########## Second turn ##########
54
+ | model | turn | score | size
55
+ |--------------------|------|-----------|--------
56
+ | gpt-4 | 2 | 9.025000 | -
57
+ | xDAN-L2-Chat-RL-v2 | 1 | 8.087500 | 30b
58
+ | claude-instant-v1 | 2 | 8.012658 | -
59
+ | xDAN-L1-Chat-RL-v1 | 2 | 7.825000 | 7b
60
+ | gpt-3.5-turbo | 2 | 7.812500 | 20b
61
+ | claude-v1 | 2 | 7.650000 | -
62
+ | wizardlm-30b | 2 | 6.887500 | 30b
63
+ | vicuna-33b-v1.3 | 2 | 6.787500 | 33b
64
+ | Llama-2-70b-chat | 2 | 6.725000 | 70b
65
 
66
  ########## Average turn##########
67
+ | model | score | size
68
+ |--------------------|-----------|--------
69
+ | gpt-4 | 8.990625 | -
70
+ | xDAN-L2-Chat-RL-v2 | 8.437500 | 30b
71
+ | xDAN-L1-Chat-RL-v1 | 8.350000 | 7b
72
+ | gpt-3.5-turbo | 7.943750 | 20b
73
+ | claude-v1 | 7.900000 | -
74
+ | vicuna-33b-v1.3 | 7.121875 | 33b
75
+ | wizardlm-30b | 7.009375 | 30b
76
+ | Llama-2-70b-chat | 6.856250 | 70b
 
77
 
78
 
79