DeepSeek-R1-Distill-Llama-70B config.json

Fields

id

sources/mbl-cfg-r1-distill-llama-70b

URL

https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/raw/main/config.json

Publisher

Hugging Face

Kind

repo

Accessed

2026-10-04

notes

num_hidden_layers 80, hidden_size 8192, num_attention_heads 64, num_key_value_heads 8, rope_theta 500000, max_position_embeddings 131072. rope_scaling {"rope_type":"llama3","factor":8.0,"high_freq_factor":4.0,"low_freq_factor":1.0,"original_max_position_embeddings":8192}. Read raw 2026-10-04.

Notes

num_hidden_layers 80, hidden_size 8192, num_attention_heads 64, num_key_value_heads 8, rope_theta 500000, max_position_embeddings 131072. rope_scaling {"rope_type":"llama3","factor":8.0,"high_freq_factor":4.0,"low_freq_factor":1.0,"original_max_position_embeddings":8192}. Read raw 2026-10-04.

Cross-references

This record references no other records.