Update README.md

README.md

@@ -44,31 +44,44 @@ import torch
 from transformers import AutoTokenizer, AutoModel, AutoConfig
 from peft import PeftModel
 
-# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs. MNTP LoRA weights are merged into the base model.
-.tokenizer = AutoTokenizer.from_pretrained("McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp")
-config = AutoConfig.from_pretrained("McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp", trust_remote_code=True)
-model = AutoModel.from_pretrained("McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp", trust_remote_code=True, config=config, torch_dtype=torch.bfloat16)
-model = PeftModel.from_pretrained(model, "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp")
-model = model.merge_and_unload() # This can take several minutes
+# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs.
+tokenizer = AutoTokenizer.from_pretrained(
+    "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp"
+)
+config = AutoConfig.from_pretrained(
+    "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp", trust_remote_code=True
+)
+model = AutoModel.from_pretrained(
+    "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp",
+    trust_remote_code=True,
+    config=config,
+    torch_dtype=torch.bfloat16,
+    device_map="cuda" if torch.cuda.is_available() else "cpu",
+)
 
-# Loading supervised model. This loads the trained LoRA weights on top of MNTP model. Hence the final weights are -- Base model + MNTP (LoRA) + supervised (LoRA).
-model = PeftModel.from_pretrained(model, "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised")
+# Loading MNTP (Masked Next Token Prediction) model.
+model = PeftModel.from_pretrained(
+    model,
+    "McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp",
+)
 
 # Wrapper for encoding and pooling operations
 l2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)
 
 # Encoding queries using instructions
-instruction = 'Given a web search query, retrieve relevant passages that answer the query:'
+instruction = (
+    "Given a web search query, retrieve relevant passages that answer the query:"
+)
 queries = [
-    [instruction, 'how much protein should a female eat'],
-    [instruction, 'summit define']
+    [instruction, "how much protein should a female eat"],
+    [instruction, "summit define"],
 ]
 q_reps = l2v.encode(queries)
 
 # Encoding documents. Instruction are not required for documents
 documents = [
     "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
-    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
+    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments.",
 ]
 d_reps = l2v.encode(documents)
 
@@ -79,8 +92,8 @@ cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))
 
 print(cos_sim)
 """
-tensor([[0.5486, 0.0554],
-        [0.0567, 0.5437]])
+tensor([[0.8180, 0.5825],
+        [0.1069, 0.1931]])
 """
 ```