DeepSeek: R1 Distill Qwen 14B
Deepseek R1 Distill Qwen 14B es un modelo de lenguaje grande destilado basado en [Qwen 2.5 14b] (https://huggingface.co/deepseek-ai/deepseek-r1-distill-qwen-14b), usando salidas de [Deepseek R1] (/Deepseek/Deepseek-R1).
Description
Deepseek R1 Distill Qwen 14B es un modelo de lenguaje grande destilado basado en [Qwen 2.5 14b] (https://huggingface.co/deepseek-ai/deepseek-r1-distill-qwen-14b), usando salidas de [Deepseek R1] (/Deepseek/Deepseek-R1).
ArchitectureАрхитектура
- Modality:
- text->text
- InputModalities:
- text
- OutputModalities:
- text
- Tokenizer:
- Qwen
- InstructionType:
- deepseek-r1
ContextAndLimits
- ContextLength:
- 32768 Tokens
- MaxResponseTokens:
- 16384 Tokens
- Moderation:
- Disabled
PricingRUB
- Request:
- ₽
- Image:
- ₽
- WebSearch:
- ₽
- InternalReasoning:
- ₽
- Prompt1KTokens:
- ₽
- Completion1KTokens:
- ₽
DefaultParameters
- Temperature:
- 0
UserComments