Instructions to use openbmb/NOSA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/NOSA-8B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/NOSA-8B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/NOSA-8B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openbmb/NOSA-8B", trust_remote_code=True)
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 openbmb/NOSA-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/NOSA-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/NOSA-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/NOSA-8B

SGLang

How to use openbmb/NOSA-8B 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 "openbmb/NOSA-8B" \
    --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": "openbmb/NOSA-8B",
		"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 "openbmb/NOSA-8B" \
        --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": "openbmb/NOSA-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/NOSA-8B with Docker Model Runner:
```
docker model run hf.co/openbmb/NOSA-8B
```

hyx21 commited on Jan 28

Commit

eaade69

verified ·

1 Parent(s): bb6b7d4

Update modeling_llama_long_infllmv2.py

Browse files

Files changed (1) hide show

modeling_llama_long_infllmv2.py +0 -3

modeling_llama_long_infllmv2.py CHANGED Viewed

@@ -50,10 +50,8 @@ from transformers.utils import (
     replace_return_docstrings,
 )
 from transformers.models.llama.configuration_llama import LlamaConfig
-from moba import moba_attn_varlen
 from functools import lru_cache
 from .cis_pooling import nosa_mean_pooling
-from native_sparse_attention.ops.triton.topk_sparse_attention import topk_sparse_attention
 from tqdm import tqdm
 import torch.cuda.nvtx as nvtx
@@ -683,7 +681,6 @@ class LlamaFlashAttention2(LlamaAttention):
         return attn_output, attn_weights, past_key_value
-from native_sparse_attention.ops.triton.topk_sparse_attention import topk_sparse_attention
 try:
     from flash_attn import flash_attn_func, flash_attn_varlen_func
     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa

     replace_return_docstrings,
 )
 from transformers.models.llama.configuration_llama import LlamaConfig
 from functools import lru_cache
 from .cis_pooling import nosa_mean_pooling
 from tqdm import tqdm
 import torch.cuda.nvtx as nvtx
         return attn_output, attn_weights, past_key_value
 try:
     from flash_attn import flash_attn_func, flash_attn_varlen_func
     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa