Text Generation
Transformers
Safetensors
English
lightning
conversational
generative
fast
efficient
great
tasks
agent
gpt
text-generation-inference
art
custom_code
Instructions to use Aobangaming/luna-1.5-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aobangaming/luna-1.5-flash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Aobangaming/luna-1.5-flash", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Aobangaming/luna-1.5-flash", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Aobangaming/luna-1.5-flash with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Aobangaming/luna-1.5-flash" # 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/luna-1.5-flash", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Aobangaming/luna-1.5-flash
- SGLang
How to use Aobangaming/luna-1.5-flash 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/luna-1.5-flash" \ --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/luna-1.5-flash", "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/luna-1.5-flash" \ --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/luna-1.5-flash", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Aobangaming/luna-1.5-flash with Docker Model Runner:
docker model run hf.co/Aobangaming/luna-1.5-flash
Upload folder using huggingface_hub
Browse files- config.json +13 -0
- configuration_luna copy.py +29 -0
- configuration_luna.py +29 -0
- luna_tokenizer.json +0 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "lightning",
|
| 3 |
+
"vocab_size": 65830,
|
| 4 |
+
"d_model": 256,
|
| 5 |
+
"nhead": 4,
|
| 6 |
+
"num_layers": 4,
|
| 7 |
+
"dropout": 0.1,
|
| 8 |
+
"max_seq_len": 160,
|
| 9 |
+
"auto_map": {
|
| 10 |
+
"AutoConfig": "configuration_lightning.LightningConfig",
|
| 11 |
+
"AutoModelForCausalLM": "modeling_lightning.LightningForCausalLM"
|
| 12 |
+
}
|
| 13 |
+
}
|
configuration_luna copy.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
class LightningConfig(PretrainedConfig):
|
| 5 |
+
model_type = "lightning"
|
| 6 |
+
|
| 7 |
+
def __init__(
|
| 8 |
+
self,
|
| 9 |
+
vocab_size=75000,
|
| 10 |
+
d_model=256,
|
| 11 |
+
nhead=4,
|
| 12 |
+
num_layers=6,
|
| 13 |
+
dropout=0.1,
|
| 14 |
+
max_seq_len=200,
|
| 15 |
+
**kwargs
|
| 16 |
+
):
|
| 17 |
+
kwargs.setdefault("tie_word_embeddings", False)
|
| 18 |
+
super().__init__(**kwargs)
|
| 19 |
+
|
| 20 |
+
self.vocab_size = vocab_size
|
| 21 |
+
self.d_model = d_model
|
| 22 |
+
self.nhead = nhead
|
| 23 |
+
self.num_layers = num_layers
|
| 24 |
+
self.dropout = dropout
|
| 25 |
+
self.max_seq_len = max_seq_len
|
| 26 |
+
|
| 27 |
+
self.num_hidden_layers = num_layers
|
| 28 |
+
self.num_attention_heads = nhead
|
| 29 |
+
self.hidden_size = d_model
|
configuration_luna.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
class LightningConfig(PretrainedConfig):
|
| 5 |
+
model_type = "lightning"
|
| 6 |
+
|
| 7 |
+
def __init__(
|
| 8 |
+
self,
|
| 9 |
+
vocab_size=75000,
|
| 10 |
+
d_model=256,
|
| 11 |
+
nhead=4,
|
| 12 |
+
num_layers=6,
|
| 13 |
+
dropout=0.1,
|
| 14 |
+
max_seq_len=200,
|
| 15 |
+
**kwargs
|
| 16 |
+
):
|
| 17 |
+
kwargs.setdefault("tie_word_embeddings", False)
|
| 18 |
+
super().__init__(**kwargs)
|
| 19 |
+
|
| 20 |
+
self.vocab_size = vocab_size
|
| 21 |
+
self.d_model = d_model
|
| 22 |
+
self.nhead = nhead
|
| 23 |
+
self.num_layers = num_layers
|
| 24 |
+
self.dropout = dropout
|
| 25 |
+
self.max_seq_len = max_seq_len
|
| 26 |
+
|
| 27 |
+
self.num_hidden_layers = num_layers
|
| 28 |
+
self.num_attention_heads = nhead
|
| 29 |
+
self.hidden_size = d_model
|
luna_tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ee65b783e97db03f9167748c7f4e636eed773aa48474aabdbef45dece730893
|
| 3 |
+
size 172775680
|