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)
Model tree for underscore2/llama3-8b-mlsubs
Base model
meta-llama/Meta-Llama-3-8B Quantized
unsloth/llama-3-8b-bnb-4bit
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "underscore2/llama3-8b-mlsubs"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "underscore2/llama3-8b-mlsubs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'