onekq-ai
/

granite-8b-code-base-4k-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

onekq commited on 25 days ago

Commit

16173e3

·

verified ·

1 Parent(s): 6ff2918

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ nf4_config = BitsAndBytesConfig(
 model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-8b-code-base-4k", quantization_config=nf4_config)
 # Load the tokenizer associated with the model
-tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-3b-code-base-2k")
 # Push the model and tokenizer to the Hugging Face hub
 model.push_to_hub("onekq-ai/granite-8b-code-base-4k-bnb-4bit", use_auth_token=True)

 model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-8b-code-base-4k", quantization_config=nf4_config)
 # Load the tokenizer associated with the model
+tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-8b-code-base-4k")
 # Push the model and tokenizer to the Hugging Face hub
 model.push_to_hub("onekq-ai/granite-8b-code-base-4k-bnb-4bit", use_auth_token=True)