mariagrandury/Meta-Llama-3.1-8B-ft-LoRA-elgrancorpus-it-gguf-q4_k_m

Model Details

Model Description

• Developed by: mariagrandury
• Model type: Language model, instruction model
• Language(s) (NLP): es
• License: apache-2.0
• Model fine-tuned from: meta-llama/Meta-Llama-3.1-8B
• Dataset used: mariagrandury/elgrancorpus-it

💡 Uses

Direct Use

This model's fine-tuning on an instructions dataset enables it to follow natural language instructions in Spanish. The direct use cases include virtual assistants and content generation.

Downstream Use

This model is an instruct model, it’s primarily intended for direct use and may not be ideal for further fine-tuning. It serves as a general model suitable for a wide range of applications. However, for specific use cases within certain domains, fine-tuning with domain-specific data may improve the model's performance.

Out-of-Scope Use

This model should not be used for production purposes without conducting a thorough assessment of risks and mitigation strategies.

⚠️ Bias, Risks, and Limitations

This model has limitations associated with both the underlying language model and the instruction tuning data. It is crucial to acknowledge that predictions generated by the model may inadvertently exhibit common deficiencies of language models, including hallucination, toxicity, and perpetuate harmful stereotypes across protected classes, identity characteristics, and sensitive, social, and occupational groups.

Recommendations

Please, when utilizing this model, exercise caution and critically assess the output to mitigate the potential impact of biased or inaccurate information.

If considering this model for production use, it is crucial to thoroughly evaluate the associated risks and adopt suitable precautions. Conduct a comprehensive assessment to address any potential biases and ensure compliance with legal and ethical standards.

📚 Training Details

Training Data

This model is based on Meta Llama 3.1 8B and has been fine-tuned using elgrancorpus-it.

It was trained 2x faster with Unsloth and Huggingface's TRL library.

⚙️ Technical Specifications

Compute Infrastructure

Hardware

This model was trained using a GPU L4 with 53 GB for 1h.

Software

We used the following libraries:

• unsloth
• transformers
• peft
• accelerate
• bitsandbytes

🌳 Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: 1 X L4 - 53 GB
• Hours used: 1
• Cloud Provider: Google
• Compute Region: Europe
• Carbon Emitted: 72W x 1h = 0.07 kWh x 0.27 kg eq. CO2/kWh = 0.02 kg eq. CO2