Instructions to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B")
model = AutoModelForCausalLM.from_pretrained("joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B

SGLang

How to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B",
    max_seq_length=2048,
)

Docker Model Runner
How to use joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B with Docker Model Runner:
```
docker model run hf.co/joyfox/DeepSeek-R1-Distill-Qwen-xhs-14B
```

DeepSeek-R1-Distill-Qwen-xhs-14B / README.md

starsfriday

Update README.md

a1cbcd4 verified 10 months ago

preview code

raw

history blame contribute delete

4.53 kB

	---
	library_name: transformers
	tags:
	- unsloth
	- trl
	- sft
	---

	# Model Card for Model ID

	根据小红书数据微调的专用于书写小红书文案的R1模型

	## Training at Chongqing Valiant Cat

	This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD(```https://vvicat.com/```).Business cooperation is welcome


	### Direct Use

	```
	from transformers import TextStreamer
	from unsloth import FastLanguageModel

	model_name = "valiantcat/DeepSeek-R1-Distill-Qwen-xhs-14B"
	model, tokenizer = FastLanguageModel.from_pretrained(
	model_name=model_name,
	max_seq_length=8192,
	load_in_4bit=True
	)

	FastLanguageModel.for_inference(model)

	question = "写一篇小红书风格的帖子，标题是男生变帅只需三步丨分享逆袭大干货"
	inputs = tokenizer([question], return_tensors="pt").to("cuda")

	streamer = TextStreamer(tokenizer)
	_ = model.generate(
	**inputs,
	streamer=streamer,
	max_new_tokens=1200,
	use_cache=True
	)
	```

	```
	<think>
	好的，用户让我写一篇小红书风格的帖子，标题是“男生变帅只需三步丨分享逆袭大干货”。首先，我需要确定目标受众。小红书的用户主要是年轻女性，但这个主题是针对男生变帅的，所以可能吸引男性读者，尤其是那些想要提升自己外在形象的人。
	接下来，我要考虑小红书帖子的特点。通常这类平台喜欢用活泼、亲切的语气，使用表情符号和分段清晰的内容结构。标题需要吸引眼球，所以用了“逆袭大干货”这样的词汇，带有激励的感觉。正文部分应该分步骤说明，每一步都有具体的建议，并且加入一些实用的小贴士。
	用户的需求是让男生通过三个步骤变帅，可能他们希望内容简单易行，不需要太多时间和金钱投入。因此，我需要确保每个步骤都是可行的，比如日常习惯、发型和穿搭，这些都是比较基础但有效的方面。
	然后，我要考虑可能没有明说的深层需求。也许有些男生觉得变帅很难，或者不知道从哪里下手，所以需要提供一个清晰的框架，让他们感觉只要跟着做就能看到效果。同时，加入一些鼓励的话语，比如“30天养成”这样的时间点，增加紧迫感和动力。
	另外，要注意避免过于专业的术语，保持语言通俗易懂。使用表情符号来增加亲和力，比如🔥、💡这些符号可以突出重点。每个步骤下还要有具体的例子，比如发型推荐或者穿搭建议，这样读者更容易理解和应用。
	最后，检查结构是否符合小红书的风格：标题吸引人，正文分点明确，每部分有小标题，结尾有互动引导，比如让读者留言分享自己的经验或提问。确保整体内容积极向上，充满正能量，符合平台调性。
	</think>

	【男生变帅只需三步丨30天逆袭被夸“脱胎换骨”！】🔥

	✨“你真的不需要花1w买奢侈品，
	每天5分钟习惯+20秒打理=素颜也能赢！”
	（附私藏干货图解版）

	💡Step 1｜「气质感从洗脸开始」
	✅每日3步水煮蛋法则：
	1️⃣ 温和洁面后用氨基酸洗面奶按压T区（拒绝搓脸！）
	2️⃣ 精华+乳液按摩至吸收，男生选含烟酰胺/玻尿酸款更清爽
	3️⃣ 每周1次泥膜敷鼻翼闭口区（黑头退退退！）

	💡Step 2｜「发型决定颜值高度」
	✅冷门但显帅王炸公式：
	✔️短发男生：C字内扣+侧分刘海=瞬间变清爽学长
	✔️中长发男生：背 undercut + 长卷度（理发店说“韩系慵懒风”就行）
	✔️油头星人必备：摩丝定型+喷雾锁死，拒绝塌鼻子！

	💡Step 3｜「穿搭心机藏在细节里」
	✅5件万能搭法则：
	1️⃣ 白衬衫+牛仔裤=永不出错基础款
	2️⃣ 毛衣配工装裤（记得露脚踝！）
	3️⃣ 卫衣叠穿技巧：内搭短袖+外挂高领打底
	4️⃣ 配饰小心机：银色耳钉/卡西欧表/帆布鞋
	5️⃣ 背包选帆布款，装书本也像在背奢侈品

	🌟私藏tips：
	✔️每天照镜子时微笑3分钟（提升眼周紧致度）
	✔️饮食加点深海鱼油+维生素E胶囊（改善暗沉发黄）
	✔️周末去健身房打个篮球（汗液能打开毛孔吸收护肤品）

	👉🏻30天打卡挑战：评论区交作业的宝子记得@我！
	（悄悄说：连我的直男同事都问我是不是偷偷打了玻尿酸…）

	#男生变帅 #逆袭干货 #形象管理 #学渣逆袭 #小红书成长记
	```