Update README.md

README.md

@@ -23,7 +23,7 @@ This model is a fine-tuned version of [BEE-spoke-data/tFINE-680m-e32-d16-gqa-102
 ## testing 
 
 
-install [transformers fork with GQA updates for t5](https://github.com/pszemraj/transformers.git) (wip):
+install [transformers fork with GQA updates for t5](https://github.com/pszemraj/transformers/tree/t5-gqa) (⚠️WIP🚧):
 
 ```sh
 pip install -U git+https://github.com/pszemraj/transformers.git@t5-gqa
@@ -36,13 +36,19 @@ then
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
 tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/tFINE-680m-e32-d16-gqa-flan")
-model = AutoModelForSeq2SeqLM.from_pretrained("BEE-spoke-data/tFINE-680m-e32-d16-gqa-flan")
+model = AutoModelForSeq2SeqLM.from_pretrained(
+    "BEE-spoke-data/tFINE-680m-e32-d16-gqa-flan"
+)
 
 prompt = "What is the capital of France?"
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
 generated_ids = model.generate(**inputs, max_new_tokens=64, no_repeat_ngram_size=3)
-print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0])
+print(
+    tokenizer.batch_decode(
+        generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
+    )[0]
+)
 ```
 
 ## Quick eval