Instructions to use LCM-Lab/nsa_llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LCM-Lab/nsa_llama with Transformers:

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

pipe = pipeline("text-generation", model="LCM-Lab/nsa_llama")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LCM-Lab/nsa_llama")
model = AutoModelForCausalLM.from_pretrained("LCM-Lab/nsa_llama")
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 LCM-Lab/nsa_llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LCM-Lab/nsa_llama

SGLang

How to use LCM-Lab/nsa_llama 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 "LCM-Lab/nsa_llama" \
    --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": "LCM-Lab/nsa_llama",
		"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 "LCM-Lab/nsa_llama" \
        --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": "LCM-Lab/nsa_llama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LCM-Lab/nsa_llama with Docker Model Runner:
```
docker model run hf.co/LCM-Lab/nsa_llama
```

QQTang1223 commited on Jan 28

Commit

fbc067b

verified ·

1 Parent(s): 38e34ab

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -46

README.md CHANGED Viewed

@@ -1,48 +1,14 @@
 ---
-license: other
-tags: []
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('younySheep/nsa_llama')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/younySheep/nsa_llama.git
-```
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>

 ---
+frameworks:
+- pytorch
+license: apache-2.0
+tasks:
+- text-generation
+language:
+- en
+base_model:
+- Llama/Llama-3.1-8B-Instruct
+pipeline_tag: text-generation
+library_name: transformers
 ---
+[Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers](https://www.arxiv.org/abs/2601.17367)