DeepSeek
DeepSeek: R1 Distill Llama 70B
Descripción del proveedor (EN)
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
ActivoFuente oficial ↗
FICHA TÉCNICA
Datos normalizados
- Id
- deepseek/deepseek-r1-distill-llama-70b
- Name
- DeepSeek: R1 Distill Llama 70B
- Provider
- DeepSeek
- Family
- deepseek-r1-distill-llama
- Source
- openrouter
- Created Unix
- 1737663169
- Knowledge Cutoff
- 2024-07-31
- Context Length
- 8192
- Source Id
- deepseek/deepseek-r1-distill-llama-70b
- Canonical Slug
- deepseek/deepseek-r1-distill-llama-70b
- Provider Slug
- deepseek
- Variant
- —
- Is Free
- False
- Max Completion Tokens
- 7372
- Modality
- text->text
- Tokenizer
- Llama3
- Instruct Type
- deepseek-r1
- Is Moderated
- False
- Supported Parameters
- ["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"]
- Default Parameters
- {}
- Reasoning
- {"mandatory":false}
- Expiration Date
- 2026-09-28
- Hugging Face Id
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Links
- {"details":"/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints"}
- Supports Tools
- False
- Supports Structured Outputs
- False
- Supports Reasoning
- True
- Supports Vision
- False
- Supports Audio
- False
- Supports Video
- False
- Supports Files
- False