Description
DeepSeek R1 Distill Llama 8B is a distilled large language model based on [Llama-3.1-8B-Instruct](/meta-llama/llama-3.1-8b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: - AIME 2024 pass@1: 50.4 - MATH-500 pass@1: 89.1 - CodeForces Rating: 1205 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Hugging Face: - [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) - [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: DeepSeek: R1 Distill Llama 8B (deepseek/deepseek-r1-distill-llama-8b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "deepseek/deepseek-r1-distill-llama-8b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the DeepSeek: R1 Distill Llama 8B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.04$ / 1M tokens
- Output: 0.04$ / 1M tokens
Token Limits
- Max Output: 32,000 tokens
- Max Context: 32,000 tokens
Subscription Tiers
- free
- pro
- ultimate