Instructions to use Aobangaming/lightning-30m-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aobangaming/lightning-30m-ft with Transformers:

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

pipe = pipeline("text-generation", model="Aobangaming/lightning-30m-ft", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Aobangaming/lightning-30m-ft", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aobangaming/lightning-30m-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aobangaming/lightning-30m-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aobangaming/lightning-30m-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aobangaming/lightning-30m-ft

SGLang

How to use Aobangaming/lightning-30m-ft 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 "Aobangaming/lightning-30m-ft" \
    --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": "Aobangaming/lightning-30m-ft",
		"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 "Aobangaming/lightning-30m-ft" \
        --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": "Aobangaming/lightning-30m-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aobangaming/lightning-30m-ft with Docker Model Runner:
```
docker model run hf.co/Aobangaming/lightning-30m-ft
```

Aobangaming commited on 20 days ago

Commit

156abfb

verified ·

1 Parent(s): d9c0069

Update modeling_lightning.py

Browse files

Files changed (1) hide show

modeling_lightning.py +2 -2

modeling_lightning.py CHANGED Viewed

@@ -2,7 +2,7 @@
 import torch
 import torch.nn as nn
-from transformers import PreTrainedModel, PretrainedConfig
 from transformers.modeling_outputs import CausalLMOutput
 import torch
@@ -190,7 +190,7 @@ class LightningConfig(PretrainedConfig):
         self.max_seq_len = max_seq_len
-class LightningForCausalLM(PreTrainedModel):
     config_class = LightningConfig
     base_model_prefix = "lightning"

 import torch
 import torch.nn as nn
+from transformers import PreTrainedModel, PretrainedConfig, GenerationMixin
 from transformers.modeling_outputs import CausalLMOutput
 import torch
         self.max_seq_len = max_seq_len
+class LightningForCausalLM(PreTrainedModel, GenerationMixin):
     config_class = LightningConfig
     base_model_prefix = "lightning"