Hugging Face's logo

webpolis
/
zenos-gpt-j-6B-instruct-4bit

Text Generation
Transformers
PyTorch
Safetensors
gptj
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Nicolas Iglesias commited on
Commit
4ab4475
•
1 Parent(s): 6e82245

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -34,10 +34,11 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
34
  tokenizer = AutoTokenizer.from_pretrained("danderian/zenos-gpt-j-6B-alpaca-evol-4bit")
35
  model = AutoModelForCausalLM.from_pretrained("danderian/zenos-gpt-j-6B-alpaca-evol-4bit")
36
 
37
- # Generate text; watch out the padding between [INST] ... [/INST]
38
  user_msg = '''Escribe un poema breve utilizando los siguientes conceptos:
39
 
40
  Bienestar, Corriente, Iluminación, Sed'''
 
 
41
  prompt = f'[INST] {user_msg} [/INST]'
42
 
43
  inputs = tokenizer(prompt, return_tensors="pt")
 
34
  tokenizer = AutoTokenizer.from_pretrained("danderian/zenos-gpt-j-6B-alpaca-evol-4bit")
35
  model = AutoModelForCausalLM.from_pretrained("danderian/zenos-gpt-j-6B-alpaca-evol-4bit")
36
 
 
37
  user_msg = '''Escribe un poema breve utilizando los siguientes conceptos:
38
 
39
  Bienestar, Corriente, Iluminación, Sed'''
40
+
41
+ # Generate text; watch out the padding between [INST] ... [/INST]
42
  prompt = f'[INST] {user_msg} [/INST]'
43
 
44
  inputs = tokenizer(prompt, return_tensors="pt")