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

Libraries

How to use inclusionAI/Ling-lite-base with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-lite-base", trust_remote_code=True)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ling-lite-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/inclusionAI/Ling-lite-base

SGLang

How to use inclusionAI/Ling-lite-base 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-lite-base" \
    --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": "inclusionAI/Ling-lite-base",
		"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 "inclusionAI/Ling-lite-base" \
        --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": "inclusionAI/Ling-lite-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

zhujiangang commited on Mar 20, 2025

Commit

c9c10d7

verified ·

1 Parent(s): 6a4f845

Update configuration_bailing_moe.py

Browse files

Files changed (1) hide show

configuration_bailing_moe.py +2 -2

configuration_bailing_moe.py CHANGED Viewed

@@ -63,7 +63,7 @@ class BailingMoeConfig(PretrainedConfig):
         self.use_sliding_window = use_sliding_window
         self.sliding_window = sliding_window
         self.max_window_layers = max_window_layers
-        self.head_dim = head_dim
         self.rope_scaling = rope_scaling
         # MoE configs
@@ -75,4 +75,4 @@ class BailingMoeConfig(PretrainedConfig):
         self.first_k_dense_replace = first_k_dense_replace
         self.output_router_logits = output_router_logits
-        super().__init__(pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs)

         self.use_sliding_window = use_sliding_window
         self.sliding_window = sliding_window
         self.max_window_layers = max_window_layers
+        self.head_dim = head_dim or self.hidden_size // self.num_attention_heads
         self.rope_scaling = rope_scaling
         # MoE configs
         self.first_k_dense_replace = first_k_dense_replace
         self.output_router_logits = output_router_logits
+        super().__init__(pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs)