create

README.md

@@ -1,6 +1,6 @@
-## bloom-7b-rl
+## chatbloom-7b
 
-This is a reinforcement learning enhanced bloom model (bloom-rl), fine-tuned based on bloom-7b (Muennighoff et al.).
+This is a RLHF enhanced bloom model (chatbloom), fine-tuned based on bloom-7b (Muennighoff et al.). This model only uses English QA datasets for RLHF training, which improves the understanding and generation of English.
 
 ### Usage
 
@@ -10,16 +10,17 @@ If you don't have a good GPU (mem > 20G) then use the code below:
 # pip install -q transformers accelerate
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-checkpoint = "hongyin/bloom-7b-rl"
+checkpoint = "hongyin/chatbloom-7b"
 
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 model = AutoModelForCausalLM.from_pretrained(checkpoint)
 
-inputs = tokenizer.encode("Translate to Chinese: I love you.", return_tensors="pt")
+inputs = tokenizer.encode("Paraphrasing the text: I love you.", return_tensors="pt")
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0]))
 
-Translate to Chinese: I love you. 翻译:我爱你
+Original ouput: Paraphrasing the text: I love you. I love you. I love you. I love
+ChatBloom ouput: Paraphrasing the text: I love you. I am a good person.
 ```
 
 If you have a good GPU (mem > 20G) then use the code below:
@@ -28,16 +29,17 @@ If you have a good GPU (mem > 20G) then use the code below:
 # pip install -q transformers accelerate
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-checkpoint = "hongyin/bloom-7b-rl"
+checkpoint = "hongyin/chatbloom-7b"
 
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype="auto", device_map="auto")
 
-inputs = tokenizer.encode("Translate to Chinese: I love you.", return_tensors="pt").to("cuda")
+inputs = tokenizer.encode("Paraphrasing the text: I love you.", return_tensors="pt").to("cuda")
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0]))
 
-Translate to Chinese: I love you. 翻译:我爱你
+Original ouput: Paraphrasing the text: I love you. I love you. I love you. I love
+ChatBloom ouput: Paraphrasing the text: I love you. I am a good person.
 ```
 
 ## Bibtex entry and citation info