rhaymison
/

Mistral-8x7b-Quantized-portuguese-luana

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

rhaymison commited on Apr 23

Commit

27c28cd

•

1 Parent(s): d4672ec

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -184,8 +184,8 @@ Important points like these help models (even smaller models like 7b) to perform
 !pip install -q -U bitsandbytes
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-model = AutoModelForCausalLM.from_pretrained("rhaymison/Mistral-24b-portuguese-luana", device_map= {"": 0})
-tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-24b-portuguese-luana")
 model.eval()
 ```

 !pip install -q -U bitsandbytes
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+model = AutoModelForCausalLM.from_pretrained("rhaymison/Mistral-8x7b-Quantized-portuguese-luana", device_map= {"": 0})
+tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-8x7b-Quantized-portuguese-luana")
 model.eval()
 ```