date3k2/llama3-8b-instruct-sharegpt

Llama-8B-Instruct-ShareGPT

• Developed by: date3k2
• License: apache-2.0
• Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit

Usage

# !pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
# !pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "date3k2/llama3-8b-instruct-sharegpt",
    max_seq_length = 2048,
    dtype = None,
    load_in_4bit = True,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

messages = [
    {"from": "human", "value": "Hãy gợi ý một số địa điểm du lịch ở Hà Nội."},
]
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)
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 512, use_cache = True)