Text Generation
Transformers
Safetensors
PyTorch
cerpt-multimodal
recursive-transformer
causal-evidence
synthetic-reasoning
text2text-generation
Instructions to use qweqwqw113/cerpt-multimodal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qweqwqw113/cerpt-multimodal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="qweqwqw113/cerpt-multimodal")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("qweqwqw113/cerpt-multimodal", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use qweqwqw113/cerpt-multimodal with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "qweqwqw113/cerpt-multimodal" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "qweqwqw113/cerpt-multimodal", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/qweqwqw113/cerpt-multimodal
- SGLang
How to use qweqwqw113/cerpt-multimodal 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 "qweqwqw113/cerpt-multimodal" \ --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": "qweqwqw113/cerpt-multimodal", "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 "qweqwqw113/cerpt-multimodal" \ --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": "qweqwqw113/cerpt-multimodal", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use qweqwqw113/cerpt-multimodal with Docker Model Runner:
docker model run hf.co/qweqwqw113/cerpt-multimodal
| { | |
| "version": "1.0", | |
| "truncation": { | |
| "direction": "Right", | |
| "max_length": 96, | |
| "strategy": "LongestFirst", | |
| "stride": 0 | |
| }, | |
| "padding": { | |
| "strategy": "BatchLongest", | |
| "direction": "Right", | |
| "pad_to_multiple_of": null, | |
| "pad_id": 0, | |
| "pad_type_id": 0, | |
| "pad_token": "[PAD]" | |
| }, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[BOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[EOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": {} | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[UNK]": 1, | |
| "[BOS]": 2, | |
| "[EOS]": 3, | |
| "Solve": 4, | |
| "the": 5, | |
| "task": 6, | |
| ".": 7, | |
| "Let": 8, | |
| "x": 9, | |
| "be": 10, | |
| "5": 11, | |
| "y": 12, | |
| "equal": 13, | |
| "plus": 14, | |
| "7": 15, | |
| "z": 16, | |
| "times": 17, | |
| "2": 18, | |
| "What": 19, | |
| "is": 20, | |
| "?": 21, | |
| "answer": 22, | |
| "24": 23, | |
| "cycle": 24, | |
| "0": 25, | |
| "operator": 26, | |
| "EXTRACT": 27, | |
| "evidence": 28, | |
| "=": 29, | |
| "valid": 30, | |
| "yes": 31, | |
| "1": 32, | |
| "BIND": 33, | |
| "+": 34, | |
| "12": 35, | |
| "SIMULATE": 36, | |
| "*": 37, | |
| "Four": 38, | |
| "items": 39, | |
| "are": 40, | |
| "ordered": 41, | |
| "by": 42, | |
| "these": 43, | |
| "rules": 44, | |
| ":": 45, | |
| "W": 46, | |
| "must": 47, | |
| "come": 48, | |
| "before": 49, | |
| "X": 50, | |
| ",": 51, | |
| "Y": 52, | |
| "Z": 53, | |
| "Which": 54, | |
| "item": 55, | |
| "first": 56, | |
| "constraint": 57, | |
| "COMPARE": 58, | |
| "CHECK": 59, | |
| "3": 60, | |
| "WRITE_RESULT": 61, | |
| "there": 62, | |
| "no": 63, | |
| "predecessor": 64, | |
| "for": 65, | |
| "A": 66, | |
| "graph": 67, | |
| "has": 68, | |
| "directed": 69, | |
| "edges": 70, | |
| "D": 71, | |
| "to": 72, | |
| "B": 73, | |
| "E": 74, | |
| "C": 75, | |
| "Starting": 76, | |
| "at": 77, | |
| "follow": 78, | |
| "outgoing": 79, | |
| "step": 80, | |
| "(": 81, | |
| "s": 82, | |
| ").": 83, | |
| "node": 84, | |
| "do": 85, | |
| "you": 86, | |
| "reach": 87, | |
| "start": 88, | |
| "running": 89, | |
| "number": 90, | |
| "-": 91, | |
| "4": 92, | |
| "Apply": 93, | |
| "operations": 94, | |
| "in": 95, | |
| "order": 96, | |
| "multiply": 97, | |
| ";": 98, | |
| "subtract": 99, | |
| "add": 100, | |
| "Give": 101, | |
| "result": 102, | |
| "initial": 103, | |
| "value": 104, | |
| "after": 105, | |
| "8": 106, | |
| "9": 107, | |
| "m": 108, | |
| "n": 109, | |
| "6": 110, | |
| "60": 111, | |
| "15": 112, | |
| "18": 113, | |
| "Start": 114, | |
| "with": 115, | |
| "Then": 116, | |
| "and": 117, | |
| "final": 118, | |
| "27": 119, | |
| "16": 120, | |
| "10": 121, | |
| "20": 122, | |
| "11": 123, | |
| "13": 124, | |
| "32": 125, | |
| "36": 126, | |
| "56": 127, | |
| "14": 128, | |
| "23": 129, | |
| "40": 130, | |
| "39": 131, | |
| "21": 132, | |
| "26": 133, | |
| "28": 134, | |
| "67": 135, | |
| "19": 136, | |
| "76": 137, | |
| "30": 138, | |
| "29": 139, | |
| "33": 140, | |
| "34": 141, | |
| "42": 142, | |
| "44": 143, | |
| "45": 144, | |
| "47": 145, | |
| "48": 146, | |
| "22": 147, | |
| "65": 148, | |
| "17": 149, | |
| "68": 150, | |
| "46": 151, | |
| "52": 152, | |
| "54": 153, | |
| "64": 154, | |
| "25": 155, | |
| "37": 156, | |
| "50": 157, | |
| "57": 158, | |
| "41": 159, | |
| "35": 160, | |
| "31": 161, | |
| "53": 162, | |
| "55": 163, | |
| "63": 164, | |
| "72": 165, | |
| "38": 166, | |
| "49": 167, | |
| "61": 168, | |
| "69": 169, | |
| "43": 170, | |
| "62": 171, | |
| "51": 172, | |
| "66": 173 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |