bongchoi commited on
Commit
c60eb2f
1 Parent(s): bf1992c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -4,11 +4,11 @@ language:
4
  - en
5
  ---
6
  # **Introduction**
7
- MoMo-70B-lora-1.8.6-DPO is trained via Direct Preference Optimization([DPO](https://arxiv.org/abs/2305.18290)) from [MoMo-70B-LoRA-V1.4](https://huggingface.co/moreh/MoMo-70B-LoRA-V1.4) as its base model, with several optimizations in hyperparameters.
8
- [MoMo-70B-LoRA-V1.4](https://huggingface.co/moreh/MoMo-70B-LoRA-V1.4) is trained via Supervised Fine-Tuning (SFT) using [LoRA](https://arxiv.org/abs/2106.09685), with the QWEN-72B model as its base-model.
9
  Note that we did not exploit any form of weight merge.
10
  For leaderboard submission, the trained weight is realigned for compatibility with llama.
11
- MoMo-70B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https://moreh.io/product), which simplifies the training of large-scale models, and AMD's MI250 GPU.
12
 
13
 
14
  ## Details
@@ -38,8 +38,8 @@ MoMo-70B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https
38
  import torch
39
  from transformers import AutoModelForCausalLM, AutoTokenizer
40
 
41
- tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-70B-lora-1.8.6-DPO")
42
  model = AutoModelForCausalLM.from_pretrained(
43
- "moreh/MoMo-70B-lora-1.8.6-DPO"
44
  )
45
  ```
 
4
  - en
5
  ---
6
  # **Introduction**
7
+ MoMo-72B-lora-1.8.6-DPO is trained via Direct Preference Optimization([DPO](https://arxiv.org/abs/2305.18290)) from [MoMo-72B-LoRA-V1.4](https://huggingface.co/moreh/MoMo-72B-LoRA-V1.4) as its base model, with several optimizations in hyperparameters.
8
+ [MoMo-72B-LoRA-V1.4](https://huggingface.co/moreh/MoMo-72B-LoRA-V1.4) is trained via Supervised Fine-Tuning (SFT) using [LoRA](https://arxiv.org/abs/2106.09685), with the QWEN-72B model as its base-model.
9
  Note that we did not exploit any form of weight merge.
10
  For leaderboard submission, the trained weight is realigned for compatibility with llama.
11
+ MoMo-72B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https://moreh.io/product), which simplifies the training of large-scale models, and AMD's MI250 GPU.
12
 
13
 
14
  ## Details
 
38
  import torch
39
  from transformers import AutoModelForCausalLM, AutoTokenizer
40
 
41
+ tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-72B-lora-1.8.6-DPO")
42
  model = AutoModelForCausalLM.from_pretrained(
43
+ "moreh/MoMo-72B-lora-1.8.6-DPO"
44
  )
45
  ```