DeepSeek-R1-Distill-Llama-8B-Hermes is a fine tuning of DeepSeek-R1-Distill-Llama-8B with the Hermes-3 dataset

Run vllm : Option for 24GB VRAM GPU

vllm serve Fredtt3/DeepSeek-R1-Distill-Llama-8B-Hermes \
  --api-key dummyapikey \
  --gpu-memory-utilization 0.9 \
  --max-model-len 4096 \
  --host 0.0.0.0 \
  --port 8000
Downloads last month
2
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Fredtt3/DeepSeek-R1-Distill-Llama-8B-Hermes

Dataset used to train Fredtt3/DeepSeek-R1-Distill-Llama-8B-Hermes