metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
base_model: unsloth/llama-3-8b-bnb-4bit
pipeline_tag: text-generation

Uploaded model

Developed by: underscore2
License: apache-2.0
Finetuned from model : unsloth/llama-3-8b-bnb-4bit

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

Usage

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "underscore2/llama3-8b-mlsubs",
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit,
    )
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
inputs = tokenizer("[POST START]: New Architecture that replaces the MLP by using literal magic", return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 1000, repetition_penalty=1.4)