Llama-3.2-LoRA-0H-1D-50F

Llama-3.2-LoRA-0H-1D-50F

This model was fine-tuned from meta-llama/Llama-3.2-3B using custom training data.

Model Details

• Model Type: Causal Language Model
• Vocabulary Size: Unknown
• Hidden Size: Unknown
• Number of Layers: Unknown
• Number of Attention Heads: Unknown
• Upload Date: 2026-08-03 08:54:12

Training Details

• Base Model: llama-3.2-3b
• Dataset: 1.jsonl
• Training Epochs: 200
• Batch Size: 10
• Learning Rate: 0.0004
• Max Length: 2048

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lamsheeper/Llama-3.2-LoRA-0H-1D-50F")
model = AutoModelForCausalLM.from_pretrained("Lamsheeper/Llama-3.2-LoRA-0H-1D-50F")

# Generate text
input_text = "Your prompt here"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Files

The following files are included in this repository:

• config.json: Model configuration
• pytorch_model.bin or model.safetensors: Model weights
• tokenizer.json: Tokenizer configuration
• tokenizer_config.json: Tokenizer settings
• special_tokens_map.json: Special tokens mapping
• training_config.json: Full training hyperparameter configuration
• dataset/1.jsonl: Training dataset used to fine-tune this model

License

This model is released under the Apache 2.0 license.