Lead Response Prediction - Llama 3.1 8B LoRA

⚠️ This is a LoRA adapter, not a full model.

You need to load it with the base model: unsloth/Meta-Llama-3.1-8B-bnb-4bit

Usage

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="MotionG-ai/lead-response-llama-8b",
    max_seq_length=4096,
    load_in_4bit=True,
)

Model Details

  • Type: LoRA Adapter
  • Base Model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
  • LoRA Rank: 16
  • Trainable Parameters: 41.9M (0.52%)
  • File Size: ~180MB
Downloads last month
3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MotionG-ai/lead-response-llama-8b

Adapter
(52)
this model