74 lines
1.4 KiB
Markdown
74 lines
1.4 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- ru
|
||
|
|
- en
|
||
|
|
- pl
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- Smart
|
||
|
|
- Code
|
||
|
|
- Speak
|
||
|
|
- Russian
|
||
|
|
- Ru
|
||
|
|
- En
|
||
|
|
- English
|
||
|
|
- Pl
|
||
|
|
- Polish
|
||
|
|
- Helpful
|
||
|
|
- Ai
|
||
|
|
- Slt
|
||
|
|
- Mini
|
||
|
|
- 1.5b
|
||
|
|
- gguf
|
||
|
|
- Transformers
|
||
|
|
- Llama.cpp
|
||
|
|
- Coder
|
||
|
|
- Helper
|
||
|
|
---
|
||
|
|
|
||
|
|
# SLT-1.5B-GoToSmart
|
||
|
|
|
||
|
|
A 1.5B parameter conversational model based on Qwen2.5-1.5B.
|
||
|
|
|
||
|
|
## Training Dataset
|
||
|
|
|
||
|
|
The model was fine-tuned on 15,000 high-quality examples.
|
||
|
|
|
||
|
|
The dataset includes:
|
||
|
|
- Natural conversations in Russian, English and Polish
|
||
|
|
- Up-to-date general knowledge (as of 2025-2026)
|
||
|
|
- Python coding tasks
|
||
|
|
- Mathematics with step-by-step explanations
|
||
|
|
- Instruction-following dialogues
|
||
|
|
|
||
|
|
|
||
|
|
## How to Use
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
import torch
|
||
|
|
|
||
|
|
model_name = "SLT-AI/SLT-1.5B-GoToSmart"
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
||
|
|
model_name,
|
||
|
|
torch_dtype=torch.bfloat16,
|
||
|
|
device_map="auto"
|
||
|
|
)
|
||
|
|
|
||
|
|
messages = [{"role": "user", "content": "Hello! How are you?"}]
|
||
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||
|
|
|
||
|
|
outputs = model.generate(
|
||
|
|
**inputs,
|
||
|
|
max_new_tokens=512,
|
||
|
|
temperature=0.7,
|
||
|
|
top_p=0.9
|
||
|
|
)
|
||
|
|
|
||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|