Text Generation
Transformers
Safetensors
English
llama
astheral
instruct
qlora
conversational
text-generation-inference
Instructions to use SEE7/Astheral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Download confirmation_outputs.json from SEE7/Astheral: direct link, hf CLI and curl.
- Browser
- Download file 6.31 kB
-
https://huggingface.co/SEE7/Astheral/resolve/main/confirmation_outputs.json
- Command line
-
hf download hf://SEE7/Astheral/confirmation_outputs.json
-
curl -L -o confirmation_outputs.json https://huggingface.co/SEE7/Astheral/resolve/main/confirmation_outputs.json
6.31 kB
| [ | |
| { | |
| "id": "confirm_csv_1", | |
| "prompt": "Output one CSV row, no header or quotes: user=Cora, age=31, city=Osaka.", | |
| "kind": "exact", | |
| "expected": "Cora,31,Osaka", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Cora,31,Osaka", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_csv_2", | |
| "prompt": "Return only a CSV value row: name=Teo; years=52; place=Riga. Do not include keys or quotes.", | |
| "kind": "exact", | |
| "expected": "Teo,52,Riga", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Teo,52,Riga", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_csv_3", | |
| "prompt": "Output only CSV values in this order: city=Tartu, person=Sara, age=41. No header or quotes.", | |
| "kind": "exact", | |
| "expected": "Tartu,Sara,41", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Tartu,Sara,41", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_csv_4", | |
| "prompt": "Output a CSV data row for user=Yara, age=36, country=Kenya. No keys, header or quotes.", | |
| "kind": "exact", | |
| "expected": "Yara,36,Kenya", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Yara,36,Kenya", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_csv_5", | |
| "prompt": "Convert product=Aster; units=9; color=Indigo into one CSV value row. No header or quotation marks.", | |
| "kind": "exact", | |
| "expected": "Aster,9,Indigo", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Aster,9,Indigo", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_csv_6", | |
| "prompt": "Return only a CSV value row for name=Zoe, identifier=Q_42, town=Graz.", | |
| "kind": "exact", | |
| "expected": "Zoe,Q_42,Graz", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "Zoe,Q_42,Graz", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_copy_1", | |
| "prompt": "Write epsilon and psi, each on its own line. Preserve their English spellings, with no other text.", | |
| "kind": "exact", | |
| "expected": "epsilon\npsi", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "epsilon\npsi", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_copy_2", | |
| "prompt": "Reply with exactly: A_B-47", | |
| "kind": "exact", | |
| "expected": "A_B-47", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "A_B-47", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_copy_3", | |
| "prompt": "Copy na\u00efve and jalape\u00f1o, each on its own line. No bullets or other text.", | |
| "kind": "exact", | |
| "expected": "na\u00efve\njalape\u00f1o", | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "na\u00efve\njalape\u00f1o", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_code_pack_adjacent", | |
| "prompt": "Write only Python code for pack_adjacent(text), returning consecutive (character, count) tuples as a list.", | |
| "kind": "code", | |
| "expected": null, | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": "assert pack_adjacent('aabbba')==[('a',2),('b',3),('a',1)]\nassert pack_adjacent('')==[]\nassert pack_adjacent('x')==[('x',1)]", | |
| "output": "```python\nfrom itertools import groupby\n\ndef pack_adjacent(text):\n return [(char, len(list(run))) for char, run in groupby(text)]\n```", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_code_compress_chars", | |
| "prompt": "Write only Python code for compress_chars(text), returning consecutive (character, count) tuples as a list.", | |
| "kind": "code", | |
| "expected": null, | |
| "mode": "instruct", | |
| "group": "confirmation", | |
| "tests": "assert compress_chars('aabbba')==[('a',2),('b',3),('a',1)]\nassert compress_chars('')==[]\nassert compress_chars('x')==[('x',1)]", | |
| "output": "```python\ndef compress_chars(text):\n result = []\n for char in text:\n if result and result[-1][0] == char:\n previous, count = result[-1]\n result[-1] = (previous, count + 1)\n else:\n result.append((char, 1))\n return result\n```", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_math_1", | |
| "prompt": "Leah had 210 credits, spent one seventh of them, then received 26 credits. What is her balance? Explain briefly.", | |
| "kind": "number", | |
| "expected": 206, | |
| "mode": "thinking", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "<think>The amount spent is 210/7 = 30. Subtract it from the original amount: 210 - 30 = 180. Add the new money: 180 + 26 = 206.</think>\nAnswer: 206", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_math_2", | |
| "prompt": "Malik had 96 tokens, spent one third, then received 11 tokens. How many tokens does he have now? Explain briefly.", | |
| "kind": "number", | |
| "expected": 75, | |
| "mode": "thinking", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "<think>The amount spent is 96/3 = 32. Subtract it from the original amount: 96 - 32 = 64. Add the new tokens: 64 + 11 = 75.</think>\nAnswer: 75", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_math_3", | |
| "prompt": "A fund starts with 231 pounds, spends one seventh, and later receives 19 pounds. What is the new balance? Explain briefly.", | |
| "kind": "number", | |
| "expected": 217, | |
| "mode": "thinking", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "<think>The amount spent is 231/7 = 33. Subtract it from the original amount: 231 - 33 = 198. Add the new money: 198 + 19 = 217.</think>\nAnswer: 217", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_time_1", | |
| "prompt": "A bus leaves at 10:48 and arrives at 13:07 on the same day. What is the elapsed journey time in minutes?", | |
| "kind": "number", | |
| "expected": 139, | |
| "mode": "thinking", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "<think>Convert the times to minutes after midnight: 10*60+48 = 648 and 13*60+7 = 787.\nThe elapsed time is 787 - 648 = 139 minutes.</think>\nAnswer: 139", | |
| "pass": true | |
| }, | |
| { | |
| "id": "confirm_time_2", | |
| "prompt": "How many minutes are in two hours and seventeen minutes? Explain briefly.", | |
| "kind": "number", | |
| "expected": 137, | |
| "mode": "thinking", | |
| "group": "confirmation", | |
| "tests": null, | |
| "output": "<think>An hour has 60 minutes. 2*60+17 = 137 minutes.</think>\nAnswer: 137.", | |
| "pass": true | |
| } | |
| ] |