tolk-7b

tolk-7B is a fine-tuned language model based on DeepSeek-R1-Distill-Qwen-7B.

The model is tailored for multi-turn conversational dialogue, persona alignment, and structured text generation across Russian and English language tasks.

📌 Model Summary

Model Name: tolk-7B

Base Architecture: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B (Qwen2 Causal LM)

Languages: Russian (ru), English (en)

Primary Task: Conversational Text Generation / Persona-based Dialogue

🚀 Quick Start (How to Use)

You can run tolk-7B using standard Hugging Face transformers:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "RaspizdAI/tolk-7B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "Привет! Расскажи немного о себе."
messages = [
    {"role": "user", "content": prompt}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
).to("cuda")

outputs = model.generate(
    input_ids=inputs,
    max_new_tokens=1024,
    temperature=0.2,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
print(response)

📜 License

This model is made available under the MIT License. You are free to use, modify, distribute, and incorporate this model into commercial or non-commercial applications.