Instructions to use OpenMOSS-Team/moss-moon-003-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMOSS-Team/moss-moon-003-sft with Transformers:

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

pipe = pipeline("text-generation", model="OpenMOSS-Team/moss-moon-003-sft", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/moss-moon-003-sft", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenMOSS-Team/moss-moon-003-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMOSS-Team/moss-moon-003-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenMOSS-Team/moss-moon-003-sft

SGLang

How to use OpenMOSS-Team/moss-moon-003-sft 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 "OpenMOSS-Team/moss-moon-003-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "OpenMOSS-Team/moss-moon-003-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMOSS-Team/moss-moon-003-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenMOSS-Team/moss-moon-003-sft with Docker Model Runner:
```
docker model run hf.co/OpenMOSS-Team/moss-moon-003-sft
```

txsun commited on Apr 19, 2023

Commit

9db9cef

1 Parent(s): f1ab6b1

Upload added_tokens.json with huggingface_hub

Browse files

Files changed (1) hide show

added_tokens.json +45 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,45 @@

+{
+  "\t\t": 106066,
+  "\t\t\t": 106065,
+  "\t\t\t\t": 106064,
+  "\t\t\t\t\t": 106063,
+  "\t\t\t\t\t\t": 106062,
+  "\t\t\t\t\t\t\t": 106061,
+  "\t\t\t\t\t\t\t\t": 106060,
+  "\t\t\t\t\t\t\t\t\t": 106059,
+  "  ": 106058,
+  "   ": 106057,
+  "    ": 106056,
+  "     ": 106055,
+  "      ": 106054,
+  "       ": 106053,
+  "        ": 106052,
+  "         ": 106051,
+  "          ": 106050,
+  "           ": 106049,
+  "            ": 106048,
+  "             ": 106047,
+  "              ": 106046,
+  "               ": 106045,
+  "                ": 106044,
+  "                 ": 106043,
+  "                  ": 106042,
+  "                   ": 106041,
+  "                    ": 106040,
+  "                     ": 106039,
+  "                      ": 106038,
+  "                       ": 106037,
+  "                        ": 106036,
+  "                         ": 106035,
+  "                          ": 106034,
+  "                           ": 106033,
+  "                            ": 106032,
+  "                             ": 106031,
+  "                              ": 106030,
+  "                               ": 106029,
+  "<eoc>": 106070,
+  "<eoh>": 106067,
+  "<eom>": 106068,
+  "<eor>": 106071,
+  "<eot>": 106069
+}