l2v = LLM2Vec.from_pretrained(#    "meta-llama/Meta-Llama-3-8B","meta-llama/Llama-2-7b-hf",    device_map="cuda" if torch.cuda.is_available() else "cpu",    torch_dtype=torch.bfloat16,)

l2v.save("Llama-2-7b-Emb")

!git clone https://github.com/McGill-NLP/llm2vec.git

JSON_CONFIG='''{"model_name_or_path": "meta-llama/Llama-2-7b-hf","dataset_name": "wikitext","dataset_config_name": "wikitext-103-raw-v1","per_device_train_batch_size": 8,"per_device_eval_batch_size": 1,"gradient_accumulation_steps": 16,"do_train": true,"do_eval": true,"max_seq_length": 512,"mask_token_type": "blank","data_collator_type": "all_mask","mlm_probability": 0.8,"overwrite_output_dir": true,"output_dir": "Llama-2-7B-llm2vec-MNTP-Emb","evaluation_strategy": "steps","eval_steps": 100,"save_steps": 200,"stop_after_n_steps": 1000,"lora_r": 16,"gradient_checkpointing": true,"torch_dtype": "bfloat16","attn_implementation": "flash_attention_2"}'''
with open("mtnp_config.json", 'w') as f:  f.write(JSON_CONFIG)

!python llm2vec/experiments/run_mntp.py mtnp_config.json

from llm2vec import LLM2Vec

import torchfrom transformers import AutoTokenizer, AutoModel, AutoConfigfrom peft import PeftModel

# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs.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,    device_map="cuda" if torch.cuda.is_available() else "cpu",)

# Loading MNTP (Masked Next Token Prediction) model.model = PeftModel.from_pretrained(    model,"McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp",)

# Wrapper for encoding and pooling operationsl2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)

# Encoding queries using instructionsinstruction = ("Given a web search query, retrieve relevant passages that answer the query:")queries = [    [instruction, "how much protein should a female eat"],    [instruction, "summit define"],]q_reps = l2v.encode(queries)

# Encoding documents. Instruction are not required for documentsdocuments = ["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.",]d_reps = l2v.encode(documents)

# Compute cosine similarityq_reps_norm = torch.nn.functional.normalize(q_reps, p=2, dim=1)d_reps_norm = torch.nn.functional.normalize(d_reps, p=2, dim=1)cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))

tensor([[0.6266, 0.4201],        [0.3415, 0.5245]])