Instructions to use FINAL-Bench/Aether-6B-11Attn-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Aether-6B-11Attn-base with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Aether-6B-11Attn-base", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Aether-6B-11Attn-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Aether-6B-11Attn-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Aether-6B-11Attn-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Aether-6B-11Attn-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Aether-6B-11Attn-base

SGLang

How to use FINAL-Bench/Aether-6B-11Attn-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 "FINAL-Bench/Aether-6B-11Attn-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": "FINAL-Bench/Aether-6B-11Attn-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 "FINAL-Bench/Aether-6B-11Attn-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": "FINAL-Bench/Aether-6B-11Attn-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FINAL-Bench/Aether-6B-11Attn-base with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Aether-6B-11Attn-base
```

SeaWolf-AI commited on 28 days ago

Commit

1158f51

verified ·

1 Parent(s): cde41f0

remove oheng/오행 references (pass 2)

Browse files

Files changed (1) hide show

aether_pkg/configuration_aether_v2_11attn.py +1 -1

aether_pkg/configuration_aether_v2_11attn.py CHANGED Viewed

@@ -34,7 +34,7 @@ class AETHERV211AttnConfig(PretrainedConfig):
     11×11 Latin Square × 121 layers
     25-expert MoE × top-7 active per token
-    5-element cyclic FFN phase (오행)
     """
     model_type = "aether_v2_11attn"
     keys_to_ignore_at_inference = ["past_key_values"]

     11×11 Latin Square × 121 layers
     25-expert MoE × top-7 active per token
+    5-element cyclic FFN phase
     """
     model_type = "aether_v2_11attn"
     keys_to_ignore_at_inference = ["past_key_values"]