Hugging Face's logo

allenai
/
tulu-2-dpo-70b

Text Generation
Transformers
PyTorch
Safetensors
English
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
11
natolambert commited on
Commit
eee6ee9
β€’
1 Parent(s): 0709c67

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -44,23 +44,23 @@ All smaller DPO'd models have strong performance per model size in the category
44
  | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
45
  |-------------|-----|----|---------------|--------------|
46
  | **Tulu-v2-7b** πŸͺ | **7B** | **dDPO** | **TODO** | **TODO** |
47
- | **Tulu-v2-13b** πŸͺ | **13B** | **dDPO** | **TODO** | **TODO** |
48
- | **Tulu-v2-70b** πŸͺ | **70B** | **dDPO** | **TODO** | **TODO** |
49
  | **Tulu-v2-dpo-7b** πŸͺ | **7B** | **dDPO** | **TODO** | **TODO** |
50
- | **Tulu-v2-dpo-13b** πŸͺ | **13B** | **dDPO** | **TODO** | **TODO** |
51
- | **Tulu-v2-dpo-70b** πŸͺ | **70B** | **dDPO** | **TODO** | **TODO** |
52
  | StableLM-Tuned-Ξ± | 7B| dSFT |2.75| -|
53
  | MPT-Chat | 7B |dSFT |5.42| -|
54
  | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
55
  | Mistral-Instructv0.1 | 7B| - | 6.84 |-|
56
  | Zephyr-7b-Ξ± |7B| dDPO| 6.88| -|
57
  | Zephyr-7b-Ξ² πŸͺ | 7B | dDPO | 7.34 | 90.60 |
 
 
58
  | Falcon-Instruct | 40B |dSFT |5.17 |45.71|
59
  | Guanaco | 65B | SFT |6.41| 71.80|
60
  | Llama2-Chat | 70B |RLHF |6.86| 92.66|
61
  | Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
62
  | WizardLM v1.0 | 70B |dSFT |7.71 |-|
63
  | Xwin-LM v0.1 | 70B |dPPO |- |95.57|
 
 
64
  | GPT-3.5-turbo | - |RLHF |7.94 |89.37|
65
  | Claude 2 | - |RLHF |8.06| 91.36|
66
  | GPT-4 | -| RLHF |8.99| 95.28|
 
44
  | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
45
  |-------------|-----|----|---------------|--------------|
46
  | **Tulu-v2-7b** πŸͺ | **7B** | **dDPO** | **TODO** | **TODO** |
 
 
47
  | **Tulu-v2-dpo-7b** πŸͺ | **7B** | **dDPO** | **TODO** | **TODO** |
 
 
48
  | StableLM-Tuned-Ξ± | 7B| dSFT |2.75| -|
49
  | MPT-Chat | 7B |dSFT |5.42| -|
50
  | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
51
  | Mistral-Instructv0.1 | 7B| - | 6.84 |-|
52
  | Zephyr-7b-Ξ± |7B| dDPO| 6.88| -|
53
  | Zephyr-7b-Ξ² πŸͺ | 7B | dDPO | 7.34 | 90.60 |
54
+ | **Tulu-v2-13b** πŸͺ | **13B** | **dDPO** | **TODO** | **TODO** |
55
+ | **Tulu-v2-dpo-13b** πŸͺ | **13B** | **dDPO** | **TODO** | **TODO** |
56
  | Falcon-Instruct | 40B |dSFT |5.17 |45.71|
57
  | Guanaco | 65B | SFT |6.41| 71.80|
58
  | Llama2-Chat | 70B |RLHF |6.86| 92.66|
59
  | Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
60
  | WizardLM v1.0 | 70B |dSFT |7.71 |-|
61
  | Xwin-LM v0.1 | 70B |dPPO |- |95.57|
62
+ | **Tulu-v2-70b** πŸͺ | **70B** | **dDPO** | **TODO** | **TODO** |
63
+ | **Tulu-v2-dpo-70b** πŸͺ | **70B** | **dDPO** | **TODO** | **TODO** |
64
  | GPT-3.5-turbo | - |RLHF |7.94 |89.37|
65
  | Claude 2 | - |RLHF |8.06| 91.36|
66
  | GPT-4 | -| RLHF |8.99| 95.28|