Text Generation
Transformers
Safetensors
Korean
English
aether_micro
Mixture of Experts
mixture-of-experts
custom
aether
latent-thought
multi-token-prediction
custom_code
Instructions to use B2J/AETHER-Micro-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use B2J/AETHER-Micro-0.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="B2J/AETHER-Micro-0.5B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("B2J/AETHER-Micro-0.5B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use B2J/AETHER-Micro-0.5B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "B2J/AETHER-Micro-0.5B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "B2J/AETHER-Micro-0.5B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/B2J/AETHER-Micro-0.5B
- SGLang
How to use B2J/AETHER-Micro-0.5B 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 "B2J/AETHER-Micro-0.5B" \ --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": "B2J/AETHER-Micro-0.5B", "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 "B2J/AETHER-Micro-0.5B" \ --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": "B2J/AETHER-Micro-0.5B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use B2J/AETHER-Micro-0.5B with Docker Model Runner:
docker model run hf.co/B2J/AETHER-Micro-0.5B
JangJaewon commited on
Fix imports for trust_remote_code: self_evaluation.py
Browse files- self_evaluation.py +2 -2
self_evaluation.py
CHANGED
|
@@ -8,7 +8,7 @@ AETHER-Micro Self-Evaluation Head
|
|
| 8 |
import torch
|
| 9 |
import torch.nn as nn
|
| 10 |
|
| 11 |
-
from configuration_aether_micro import AETHERMicroConfig
|
| 12 |
|
| 13 |
|
| 14 |
class AETHERMicroSelfEvalHead(nn.Module):
|
|
@@ -101,7 +101,7 @@ def count_self_eval_parameters(config: AETHERMicroConfig) -> int:
|
|
| 101 |
|
| 102 |
|
| 103 |
if __name__ == "__main__":
|
| 104 |
-
from configuration_aether_micro import AETHERMicroConfig
|
| 105 |
|
| 106 |
config = AETHERMicroConfig()
|
| 107 |
param_count = count_self_eval_parameters(config)
|
|
|
|
| 8 |
import torch
|
| 9 |
import torch.nn as nn
|
| 10 |
|
| 11 |
+
from .configuration_aether_micro import AETHERMicroConfig
|
| 12 |
|
| 13 |
|
| 14 |
class AETHERMicroSelfEvalHead(nn.Module):
|
|
|
|
| 101 |
|
| 102 |
|
| 103 |
if __name__ == "__main__":
|
| 104 |
+
from .configuration_aether_micro import AETHERMicroConfig
|
| 105 |
|
| 106 |
config = AETHERMicroConfig()
|
| 107 |
param_count = count_self_eval_parameters(config)
|