Uploaded model

Developed by: alibidaran
License: apache-2.0
Finetuned from model : unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Direct usage:

from unsloth import FastLanguageModel
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "alibidaran/LLAMA3-intructive_reasoning", # YOUR MODEL YOU USED FOR TRAINING
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit,
    )
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
system_prompt="""
    You are a reasonable expert who thinks and answer the users question. 
    Before respond first think and create a chain of thoughts in your mind. 
    Then respond to the client. 
    Your chain of thought and reflection must be in <thinking>..</thinking> format and your respond 
    should be in the <output>..</output> format. 
    """

messages = [
    {'role':'system','content':system_prompt},
    {"role": "user", "content":'Explain the concept of the Twin Flame Mirror and its significance in the Twin Flame journey.' },

]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer, skip_prompt = True)
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens =2048,
                   use_cache = True, temperature = 0.5, min_p = 0.9)