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)

# pip install -U transformers accelerate
# 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 27 days ago

Commit

22ddb49

verified ·

1 Parent(s): 72f0568

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -36

README.md CHANGED Viewed

@@ -73,45 +73,10 @@ and add necessary guardrails and precautions to prevent misuse.
 Use the code below to get started with the model.
 ```python
-import sys
-import types
 import torch
-from transformers import PretrainedConfig, AutoModelForCausalLM
 from tokenizers import Tokenizer
-class LightningConfig(PretrainedConfig):
-    model_type = "lightning"
-    def __init__(
-        self,
-        vocab_size=50000,
-        d_model=256,
-        nhead=4,
-        num_layers=4,
-        dropout=0.1,
-        max_seq_len=160,
-        **kwargs
-    ):
-        super().__init__(
-            tie_word_embeddings=False,
-            **kwargs
-        )
-        self.vocab_size = vocab_size
-        self.d_model = d_model
-        self.nhead = nhead
-        self.num_layers = num_layers
-        self.dropout = dropout
-        self.max_seq_len = max_seq_len
-config_module = types.ModuleType("configuration_lightning")
-config_module.LightningConfig = LightningConfig
-sys.modules["configuration_lightning"] = config_module
 model_id = "Aobangaming/lightning-30m-ft"
 model = AutoModelForCausalLM.from_pretrained(
@@ -135,6 +100,7 @@ outputs = model.generate(
 )
 print(tokenizer.decode(outputs[0].tolist()))
 ```
 ## Training Details

 Use the code below to get started with the model.
 ```python
 import torch
+from transformers import AutoModelForCausalLM
 from tokenizers import Tokenizer
 model_id = "Aobangaming/lightning-30m-ft"
 model = AutoModelForCausalLM.from_pretrained(
 )
 print(tokenizer.decode(outputs[0].tolist()))
 ```
 ## Training Details