Jr12lm12/llama-3.1-8b-climate-expert-gguf

Climate Expert Model - Llama 3.1 8B Fine-tuned

This model is a fine-tuned version of Meta-Llama-3.1-8B-Instruct for climate change claim classification.

Model Description

• Base Model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
• Fine-tuning Dataset: tdiggelm/climate_fever
• Task: Climate change claim classification
• Labels: SUPPORTS, REFUTES, NOT_ENOUGH_INFO, DISPUTED

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Jr12lm12/llama-3.1-8b-climate-expert-gguf")
tokenizer = AutoTokenizer.from_pretrained("Jr12lm12/llama-3.1-8b-climate-expert-gguf")

messages = [
    {"role": "system", "content": "You are a climate expert that evaluates climate change claims. Answer with SUPPORTS, REFUTES, or NOT_ENOUGH_INFO."},
    {"role": "user", "content": "Rising global temperatures are causing glaciers to melt."},
]

inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=128)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Convert to GGUF (Local)

If you need GGUF format, you can convert locally:

# Install llama.cpp
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp && make

# Download and convert
huggingface-cli download Jr12lm12/llama-3.1-8b-climate-expert-gguf --local-dir ./model
python convert_hf_to_gguf.py ./model --outtype f16 --outfile model.gguf
./llama-quantize model.gguf model-q4_k_m.gguf q4_k_m

Training Details

• Training samples: 1381
• Validation samples: 154
• Epochs: 3
• Learning rate: 2e-4
• LoRA rank: 16
• LoRA alpha: 16
• Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Performance

The model was trained using LoRA (Low-Rank Adaptation) on the Climate FEVER dataset for classifying climate change claims.

License

This model inherits the license from the base Llama 3.1 model.