Instructions to use FINAL-Bench/Aether-7B-5Attn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Aether-7B-5Attn with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Aether-7B-5Attn", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Aether-7B-5Attn", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Aether-7B-5Attn with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Aether-7B-5Attn"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Aether-7B-5Attn",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Aether-7B-5Attn

SGLang

How to use FINAL-Bench/Aether-7B-5Attn 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-7B-5Attn" \
    --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": "FINAL-Bench/Aether-7B-5Attn",
		"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 "FINAL-Bench/Aether-7B-5Attn" \
        --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": "FINAL-Bench/Aether-7B-5Attn",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Aether-7B-5Attn with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Aether-7B-5Attn
```

SeaWolf-AI commited on 7 days ago

Commit

21574a6

verified ·

1 Parent(s): a2748f2

sanitize: internal paths/ids/comments

Browse files

Files changed (1) hide show

eval/lmeval_run.py +3 -3

eval/lmeval_run.py CHANGED Viewed

@@ -4,7 +4,7 @@ os.environ["CUDA_VISIBLE_DEVICES"] = os.environ.get("GPU", "2")
 os.environ.setdefault("HF_DATASETS_TRUST_REMOTE_CODE", "1")
 import sys, json, importlib.util, torch
-MODEL = os.environ.get("MODEL", "/NHNHOME/WORKSPACE/0426030036_A/aether_final_annealed")
 MERGE_ADAPTER = os.environ.get("MERGE_ADAPTER", "")
 ADAPTER = os.environ.get("ADAPTER", "")
 TAG = os.environ.get("TAG", "annealed")
@@ -53,6 +53,6 @@ for t in TASKS:
     f = lambda v: ("%6.1f" % (100 * v)) if isinstance(v, float) else "     -"
     print("%-18s %8s %8s   %8s %8s" % (t, f(a), f(ae), f(n), f(ne)), flush=True)
 print("-" * 60, flush=True)
-json.dump(out, open("/NHNHOME/lmeval_%s.json" % TAG, "w"), indent=2, ensure_ascii=False)
-print("[saved] /NHNHOME/lmeval_%s.json" % TAG, flush=True)
 print("LMEVAL_DONE", flush=True)

 os.environ.setdefault("HF_DATASETS_TRUST_REMOTE_CODE", "1")
 import sys, json, importlib.util, torch
+MODEL = os.environ.get("MODEL", "/workspace/aether-annealed")
 MERGE_ADAPTER = os.environ.get("MERGE_ADAPTER", "")
 ADAPTER = os.environ.get("ADAPTER", "")
 TAG = os.environ.get("TAG", "annealed")
     f = lambda v: ("%6.1f" % (100 * v)) if isinstance(v, float) else "     -"
     print("%-18s %8s %8s   %8s %8s" % (t, f(a), f(ae), f(n), f(ne)), flush=True)
 print("-" * 60, flush=True)
+json.dump(out, open("/workspace/lmeval_%s.json" % TAG, "w"), indent=2, ensure_ascii=False)
+print("[saved] /workspace/lmeval_%s.json" % TAG, flush=True)
 print("LMEVAL_DONE", flush=True)