DeepSeek-R1-Distill-Qwen-7B

Mirror of DeepSeek R1 Distill Qwen 7B weights, hosted by ljsysfurry.

Original: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Companion LoRA (Chinese Novel)

ljsysfurry/deepseek-r1-7b-novel-lora
Fine-tuned on 260K words Chinese novel. Story continuation + character dialogue.

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("ljsysfurry/DeepSeek-R1-Distill-Qwen-7B")
tokenizer = AutoTokenizer.from_pretrained("ljsysfurry/DeepSeek-R1-Distill-Qwen-7B")

本仓库为 DeepSeek R1 7B 的完整权重备份。

Downloads last month
18
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support