rm prefix from tests

README.md

@@ -98,4 +98,7 @@ BLOCK_UID=bigscience/test-bloomd-6b3.4 pytest tests/test_block_exact_match.py
 
 # the test below will fail because there is no server that serves layer 7
 # BLOCK_UID=bigscience/test-bloomd-6b3.7 pytest tests/test_block_exact_match.py
+
+
+BLOCK_UID=bigscience/test-bloomd-6b3.4 pytest tests/test_block_exact_match.py
 ```

tests/test_full_model.py

@@ -26,7 +26,7 @@ REF_NAME = os.environ.get("REF_NAME")
 
 def test_full_model_exact_match(atol_forward=1e-5, atol_inference=1e-3, prefix="bloom6b3"):
     tokenizer = transformers.BloomTokenizerFast.from_pretrained(MODEL_NAME)
-    model = DistributedBloomForCausalLM.from_pretrained(MODEL_NAME, initial_peers=INITIAL_PEERS, prefix=prefix)
+    model = DistributedBloomForCausalLM.from_pretrained(MODEL_NAME, initial_peers=INITIAL_PEERS)
     assert len(model.transformer.h) == model.config.n_layer
 
     test_inputs = tokenizer("A cat sat on a mat", return_tensors="pt")["input_ids"]