← Volver al catálogo
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...

deepseek-r1-distill-llamaopenrouterPor validar
Contexto8.192 tokens
Publicado23/01/2025
Corte de conocimiento2024-07-31
EstadoActivo
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