Instructions to use SEE7/Astheral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SEE7/Astheral with Transformers:

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

pipe = pipeline("text-generation", model="SEE7/Astheral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SEE7/Astheral")
model = AutoModelForCausalLM.from_pretrained("SEE7/Astheral", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SEE7/Astheral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SEE7/Astheral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SEE7/Astheral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SEE7/Astheral

SGLang

How to use SEE7/Astheral 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 "SEE7/Astheral" \
    --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": "SEE7/Astheral",
		"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 "SEE7/Astheral" \
        --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": "SEE7/Astheral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SEE7/Astheral with Docker Model Runner:
```
docker model run hf.co/SEE7/Astheral
```

Astheral / expanded-evaluation /long_output_test.json

SEE7

Record real 800-token generation test beyond previous output cap

09d2f18 verified 2 days ago

Raw History Blame Contribute Delete

2.12 kB

{
  "model_revision": "37adef9b3917e4a3de0bb77f0db71089b7b82202",
  "max_new_tokens": 1024,
  "max_time_seconds": 110,
  "generated_tokens": 800,
  "elapsed_seconds": 30.515983065999535,
  "passed_old_cap": true,
  "output": "1\n2\n3\n4\n5\n6\n7\n8\n9\n10\n11\n12\n13\n14\n15\n16\n17\n18\n19\n20\n21\n22\n23\n24\n25\n26\n27\n28\n29\n30\n31\n32\n33\n34\n35\n36\n37\n38\n39\n40\n41\n42\n43\n44\n45\n46\n47\n48\n49\n50\n51\n52\n53\n54\n55\n56\n57\n58\n59\n60\n61\n62\n63\n64\n65\n66\n67\n68\n69\n70\n71\n72\n73\n74\n75\n76\n77\n78\n79\n80\n81\n82\n83\n84\n85\n86\n87\n88\n89\n90\n91\n92\n93\n94\n95\n96\n97\n98\n99\n100\n101\n102\n103\n104\n105\n106\n107\n108\n109\n110\n111\n112\n113\n114\n115\n116\n117\n118\n119\n120\n121\n122\n123\n124\n125\n126\n127\n128\n129\n130\n131\n132\n133\n134\n135\n136\n137\n138\n139\n140\n141\n142\n143\n144\n145\n146\n147\n148\n149\n150\n151\n152\n153\n154\n155\n156\n157\n158\n159\n160\n161\n162\n163\n164\n165\n166\n167\n168\n169\n170\n171\n172\n173\n174\n175\n176\n177\n178\n179\n180\n181\n182\n183\n184\n185\n186\n187\n188\n189\n190\n191\n192\n193\n194\n195\n196\n197\n198\n199\n200\n201\n202\n203\n204\n205\n206\n207\n208\n209\n210\n211\n212\n213\n214\n215\n216\n217\n218\n219\n220\n221\n222\n223\n224\n225\n226\n227\n228\n229\n230\n231\n232\n233\n234\n235\n236\n237\n238\n239\n240\n241\n242\n243\n244\n245\n246\n247\n248\n249\n250\n251\n252\n253\n254\n255\n256\n257\n258\n259\n260\n261\n262\n263\n264\n265\n266\n267\n268\n269\n270\n271\n272\n273\n274\n275\n276\n277\n278\n279\n280\n281\n282\n283\n284\n285\n286\n287\n288\n289\n290\n291\n292\n293\n294\n295\n296\n297\n298\n299\n300\n301\n302\n303\n304\n305\n306\n307\n308\n309\n310\n311\n312\n313\n314\n315\n316\n317\n318\n319\n320\n321\n322\n323\n324\n325\n326\n327\n328\n329\n330\n331\n332\n333\n334\n335\n336\n337\n338\n339\n340\n341\n342\n343\n344\n345\n346\n347\n348\n349\n350\n351\n352\n353\n354\n355\n356\n357\n358\n359\n360\n361\n362\n363\n364\n365\n366\n367\n368\n369\n370\n371\n372\n373\n374\n375\n376\n377\n378\n379\n380\n381\n382\n383\n384\n385\n386\n387\n388\n389\n390\n391\n392\n393\n394\n395\n396\n397\n398\n399\n400"
}

	{
	"model_revision": "37adef9b3917e4a3de0bb77f0db71089b7b82202",
	"max_new_tokens": 1024,
	"max_time_seconds": 110,
	"generated_tokens": 800,
	"elapsed_seconds": 30.515983065999535,
	"passed_old_cap": true,
	"output": "1\n2\n3\n4\n5\n6\n7\n8\n9\n10\n11\n12\n13\n14\n15\n16\n17\n18\n19\n20\n21\n22\n23\n24\n25\n26\n27\n28\n29\n30\n31\n32\n33\n34\n35\n36\n37\n38\n39\n40\n41\n42\n43\n44\n45\n46\n47\n48\n49\n50\n51\n52\n53\n54\n55\n56\n57\n58\n59\n60\n61\n62\n63\n64\n65\n66\n67\n68\n69\n70\n71\n72\n73\n74\n75\n76\n77\n78\n79\n80\n81\n82\n83\n84\n85\n86\n87\n88\n89\n90\n91\n92\n93\n94\n95\n96\n97\n98\n99\n100\n101\n102\n103\n104\n105\n106\n107\n108\n109\n110\n111\n112\n113\n114\n115\n116\n117\n118\n119\n120\n121\n122\n123\n124\n125\n126\n127\n128\n129\n130\n131\n132\n133\n134\n135\n136\n137\n138\n139\n140\n141\n142\n143\n144\n145\n146\n147\n148\n149\n150\n151\n152\n153\n154\n155\n156\n157\n158\n159\n160\n161\n162\n163\n164\n165\n166\n167\n168\n169\n170\n171\n172\n173\n174\n175\n176\n177\n178\n179\n180\n181\n182\n183\n184\n185\n186\n187\n188\n189\n190\n191\n192\n193\n194\n195\n196\n197\n198\n199\n200\n201\n202\n203\n204\n205\n206\n207\n208\n209\n210\n211\n212\n213\n214\n215\n216\n217\n218\n219\n220\n221\n222\n223\n224\n225\n226\n227\n228\n229\n230\n231\n232\n233\n234\n235\n236\n237\n238\n239\n240\n241\n242\n243\n244\n245\n246\n247\n248\n249\n250\n251\n252\n253\n254\n255\n256\n257\n258\n259\n260\n261\n262\n263\n264\n265\n266\n267\n268\n269\n270\n271\n272\n273\n274\n275\n276\n277\n278\n279\n280\n281\n282\n283\n284\n285\n286\n287\n288\n289\n290\n291\n292\n293\n294\n295\n296\n297\n298\n299\n300\n301\n302\n303\n304\n305\n306\n307\n308\n309\n310\n311\n312\n313\n314\n315\n316\n317\n318\n319\n320\n321\n322\n323\n324\n325\n326\n327\n328\n329\n330\n331\n332\n333\n334\n335\n336\n337\n338\n339\n340\n341\n342\n343\n344\n345\n346\n347\n348\n349\n350\n351\n352\n353\n354\n355\n356\n357\n358\n359\n360\n361\n362\n363\n364\n365\n366\n367\n368\n369\n370\n371\n372\n373\n374\n375\n376\n377\n378\n379\n380\n381\n382\n383\n384\n385\n386\n387\n388\n389\n390\n391\n392\n393\n394\n395\n396\n397\n398\n399\n400"
	}