Instructions to use inclusionAI/Ling-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-plus with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-plus", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-plus", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/Ling-plus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/inclusionAI/Ling-plus

SGLang

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

Docker Model Runner
How to use inclusionAI/Ling-plus with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-plus
```

zhujiangang commited on Mar 14, 2025

Commit

227f47c

verified ·

1 Parent(s): 019becf

Update config.json

Browse files

Files changed (1) hide show

config.json +10 -5

config.json CHANGED Viewed

@@ -21,13 +21,17 @@
     "num_experts": 64,
     "num_shared_experts": 1,
     "norm_topk_prob": true,
-    "num_attention_heads": 42,
     "num_experts_per_tok": 4,
     "num_hidden_layers": 88,
-    "num_key_value_heads": 6,
     "pretraining_tp": 1,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
     "rope_theta": 600000,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
@@ -40,5 +44,6 @@
     "embedding_dropout": 0.0,
     "norm_head": true,
     "norm_softmax": false,
-    "output_dropout": 0.0
 }

     "num_experts": 64,
     "num_shared_experts": 1,
     "norm_topk_prob": true,
+    "num_attention_heads": 56,
     "num_experts_per_tok": 4,
     "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
     "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 4.0,
+        "original_max_position_embeddings": 16384,
+        "type": "yarn"
+    },
     "rope_theta": 600000,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
     "embedding_dropout": 0.0,
     "norm_head": true,
     "norm_softmax": false,
+    "output_dropout": 0.0,
+    "head_dim": 128
 }