Fine-tuned LLaMA 3.2 1B Instruct (Merged) – HTML Chunk Generator

This model merges a LoRA adapter into LLaMA 3.2 1B Instruct for structured HTML generation in chunked formats.

Usage (vLLM)

export HF_TOKEN=your_token
vllm serve jasongraydon01/hawkpartners-survey-llama-3.2-1b-instruct --max-model-len 32768

Usage (Transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jasongraydon01/hawkpartners-survey-llama-3.2-1b-instruct")
model = AutoModelForCausalLM.from_pretrained("jasongraydon01/hawkpartners-survey-llama-3.2-1b-instruct", torch_dtype="auto")

messages = [{
    "role": "user",
    "content": "Generate a full HTML article on the topic of..."
}]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs.input_ids, max_new_tokens=8192)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Downloads last month
11
Safetensors
Model size
1.24B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for jasongraydon01/hawkpartners-survey-llama-3.2-1b-instruct

Finetuned
(1028)
this model