67 lines
3.8 KiB
Markdown
67 lines
3.8 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
- ru
|
|
license: apache-2.0
|
|
pipeline_tag: text-generation
|
|
base_model:
|
|
- nyuuzyou/SmolLM2-360M-Eagle
|
|
datasets: nyuuzyou/EagleSFT
|
|
co2_eq_emissions:
|
|
emissions: 5484
|
|
source: Calculated based on power consumption and regional carbon intensity
|
|
training_type: fine-tuning
|
|
geographical_location: Saint-Petersburg, Russia
|
|
hardware_used: 1 RTX 4090 GPU
|
|
---
|
|
# SmolLM2-360M-Eagle-GGUF
|
|
|
|
SmolLM2-360M-Eagle-GGUF is a GGUF conversion of the [SmolLM2-360M-Eagle](https://huggingface.co/nyuuzyou/SmolLM2-360M-Eagle) model, which itself is a fine-tuned version of [SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on the [EagleSFT](https://huggingface.co/datasets/nyuuzyou/EagleSFT) dataset. This model is designed to improve capabilities in both Russian and English language tasks while being optimized for efficient local deployment.
|
|
|
|
## Model Description
|
|
SmolLM2-360M-Eagle is a lightweight language model that has been fine-tuned specifically to handle bilingual content. This fine-tuning extends the base model's capabilities to better understand and generate content in Russian while maintaining its English competency.
|
|
|
|
### Base Model
|
|
The model is built upon SmolLM2-360M, a compact language model with 360 million parameters that offers a good balance between performance and resource requirements.
|
|
|
|
## Fine-tuning Details
|
|
### Dataset
|
|
The model was fine-tuned on the EagleSFT dataset, which contains 536,231 pairs of human questions and machine-generated responses in both Russian and English languages. The dataset primarily focuses on educational content but also includes everyday questions and casual conversations.
|
|
|
|
### Environmental Impact
|
|
- **Training duration**: 41h 14m total in Saint-Petersburg, Russia
|
|
- **Power consumption**: 380W average
|
|
- **Hardware**: 1 x RTX 4090
|
|
- **Carbon emissions**: Approximately 5.48 kg CO2eq
|
|
- Calculated based on average power consumption and average CO2eq/kWh (350g) in this region
|
|
- Saint-Petersburg: 380W * 41.23h * 350g/kWh = 5.48 kg CO2eq
|
|
|
|
### Training Parameters
|
|
- **Training approach**: Supervised Fine-Tuning (SFT)
|
|
- **Training epochs**: 2
|
|
- **Learning rate**: 3.0e-04
|
|
- **Precision**: bfloat16
|
|
|
|
## Limitations and Capabilities
|
|
It's important to note that this model was not pre-trained but only underwent SFT on a relatively small number of tokens. This means that the model has a limited amount of data to rely on when answering in Russian compared to its English capabilities.
|
|
|
|
Despite extensive limitations, the model shows minimal improvement in:
|
|
- Basic recognition of Russian prompts (though with frequent misunderstandings)
|
|
- Handling simple tasks formatted as "{question in Russian}, answer in English"
|
|
- Basic translation from Russian to English (though quality remains poor)
|
|
|
|
The model's minimal understanding of Russian language comes solely from the supervised fine-tuning process without any proper pre-training with Russian text corpus, resulting in severely limited capabilities.
|
|
|
|
## Experimental Capabilities
|
|
The model demonstrates some experimental capabilities, but with significant limitations:
|
|
- Basic Russian text understanding (with frequent errors and misinterpretations)
|
|
- Limited question answering in Russian (quality significantly lower than English)
|
|
- Basic Russian to English translation (better than English to Russian)
|
|
|
|
## Limitations
|
|
- **NOT SUITABLE FOR PRODUCTION USE**: This model should not be used in production environments in any form
|
|
- Extremely limited knowledge base for Russian language due to lack of pre-training with Russian text
|
|
- Unoptimized tokenizer performance for Russian language results in inefficient token usage
|
|
- Output quality in Russian will be unsatisfactory for most use cases
|
|
- May produce inaccurate, inconsistent, or inappropriate responses, especially in Russian
|
|
- All limitations of the base SmolLM2-360M model still apply |