Text Generation
Transformers
Safetensors
English
Hindi
llama
text-to-json
home-automation
tiny-model
from-scratch
experimental
edge-ai
conversational
text-generation-inference
Instructions to use sraivante/superfast-tiny-home-robotics-json-1m-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sraivante/superfast-tiny-home-robotics-json-1m-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sraivante/superfast-tiny-home-robotics-json-1m-v1") 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("sraivante/superfast-tiny-home-robotics-json-1m-v1") model = AutoModelForCausalLM.from_pretrained("sraivante/superfast-tiny-home-robotics-json-1m-v1", 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 sraivante/superfast-tiny-home-robotics-json-1m-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sraivante/superfast-tiny-home-robotics-json-1m-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sraivante/superfast-tiny-home-robotics-json-1m-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sraivante/superfast-tiny-home-robotics-json-1m-v1
- SGLang
How to use sraivante/superfast-tiny-home-robotics-json-1m-v1 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 "sraivante/superfast-tiny-home-robotics-json-1m-v1" \ --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": "sraivante/superfast-tiny-home-robotics-json-1m-v1", "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 "sraivante/superfast-tiny-home-robotics-json-1m-v1" \ --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": "sraivante/superfast-tiny-home-robotics-json-1m-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use sraivante/superfast-tiny-home-robotics-json-1m-v1 with Docker Model Runner:
docker model run hf.co/sraivante/superfast-tiny-home-robotics-json-1m-v1
Download release_manifest.json from sraivante/superfast-tiny-home-robotics-json-1m-v1: direct link, hf CLI and curl.
- Browser
- Download file 11.8 kB
-
https://huggingface.co/sraivante/superfast-tiny-home-robotics-json-1m-v1/resolve/main/release_manifest.json
- Command line
-
hf download hf://sraivante/superfast-tiny-home-robotics-json-1m-v1/release_manifest.json
-
curl -L -o release_manifest.json https://huggingface.co/sraivante/superfast-tiny-home-robotics-json-1m-v1/resolve/main/release_manifest.json
11.8 kB
| { | |
| "release_date": "2026-09-25", | |
| "version": "v1.0.2", | |
| "publisher": "sraivante", | |
| "authorization": "Publisher explicitly requested model and dataset publication on 2026-09-25.", | |
| "copyright": "Copyright (c) 2026 sraivante, limited to original contributions and selection/arrangement.", | |
| "license": "Apache-2.0 for original release material; third-party rights unchanged.", | |
| "training_source_sha256": "10822f6617d2cc94dca66d609a1f41769cd5ef2ebba224d85fc7ae79cfbbaeba", | |
| "training_manifest_sha256": "2ead74207a38ad593819da12c52392bad8a273cc62e6842a8278ebffaa561eaa", | |
| "original_source_revision": "Not provided; original content SHA-256 is the authoritative identity.", | |
| "split_counts": { | |
| "train": 910114, | |
| "validation": 103089, | |
| "test": 104723 | |
| }, | |
| "fine_tuning": "None; trained from random initialization in a single pass.", | |
| "stress_suite_sha256": "30cb9a6de18cc12cefcbb6e1aac8a29c7371b0f4ea537e516f38d02b3f417d6c", | |
| "repository": "sraivante/superfast-tiny-home-robotics-json-1m-v1", | |
| "repository_type": "model", | |
| "dataset": { | |
| "repo_id": "sraivante/home-commands-json-v1", | |
| "revision": "v1.0.2", | |
| "commit": "8479d12161767c5aabd7dfc097e6f6c41790201a" | |
| }, | |
| "weights_sha256": "7eed2ed8eb5455f4195cba48ff38b2bc8ff8228cefaf7ee6c477200c776a8ea3", | |
| "packaging_changes": [ | |
| "Single-user chat template equivalent to training encode_prompt.", | |
| "tokenizer model_max_length metadata corrected from 256 to the trained 128-token context.", | |
| "License, cards, usage examples and release metadata added; weights and token IDs unchanged.", | |
| "Personal training-account email removed from the public notebook and notebook builder.", | |
| "Tokenizer model_input_names set to input_ids and attention_mask for standard Llama generation." | |
| ], | |
| "history_note": "Historical manifest and assessment describe their pre-publication state and are preserved; this release supersedes packaging/authorization notes.", | |
| "files": { | |
| ".gitattributes": { | |
| "bytes": 225, | |
| "sha256": "633cb3e3cbb1786e5720773279fea79d68ff4aa43dc9007a402c42ba528d6ad0" | |
| }, | |
| "LICENSE": { | |
| "bytes": 11357, | |
| "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4" | |
| }, | |
| "NOTICE": { | |
| "bytes": 728, | |
| "sha256": "3dce4a2870f76ab3b86cc84067bb017d32e8b726892fc87a8ca4110cac79219b" | |
| }, | |
| "README.md": { | |
| "bytes": 13223, | |
| "sha256": "c9b17df3dda1b3575b3add8274a2c41b39bbd262e803fe50d57f98e8a49cc28b" | |
| }, | |
| "allowed_outputs.json": { | |
| "bytes": 2590, | |
| "sha256": "317d35bd27a25e6db66deea50112633b63f7eae907178cc7f50f12dd8ad6aba1" | |
| }, | |
| "assessment/RASPBERRY_PI.md": { | |
| "bytes": 709, | |
| "sha256": "44e705c5bbf3c3488738170fc831418543d572a4a929d4c58bfeeb721b6d192d" | |
| }, | |
| "assessment/benchmark_device.py": { | |
| "bytes": 6302, | |
| "sha256": "4a188470cb99e67fb804bb0fbdc3def5ae6751fdf686ae15476604d4862ab552" | |
| }, | |
| "assessment/build_challenge.py": { | |
| "bytes": 10121, | |
| "sha256": "4d697aba3c76163acb4d3a367d45cd2126345afd3a1fc51df6336981eaf0bc3b" | |
| }, | |
| "assessment/evaluate_edge.py": { | |
| "bytes": 5579, | |
| "sha256": "8df51447b3b6416bc551bced731a4ea732a32a13a2693247ae239f71450356f4" | |
| }, | |
| "assessment/robotics_edge_v1/REPORT.md": { | |
| "bytes": 10707, | |
| "sha256": "64c6e4aa8a79ef4ca070fc72682fecff09cd20bc15f5c084b60280a5a6ea270d" | |
| }, | |
| "assessment/robotics_edge_v1/cases.jsonl": { | |
| "bytes": 95602, | |
| "sha256": "30cb9a6de18cc12cefcbb6e1aac8a29c7371b0f4ea537e516f38d02b3f417d6c" | |
| }, | |
| "assessment/robotics_edge_v1/desktop_cpu_1thread.json": { | |
| "bytes": 8389, | |
| "sha256": "36dbd74d368d7f102165b12f691a26e519e9fb4255b75392c7fd31707d16f335" | |
| }, | |
| "assessment/robotics_edge_v1/desktop_cpu_4threads.json": { | |
| "bytes": 8390, | |
| "sha256": "a244a02a1f4947b94668f9a2796a361549691bb50a335b9ab83cd19f25918a0b" | |
| }, | |
| "assessment/robotics_edge_v1/hf_compatibility.json": { | |
| "bytes": 457, | |
| "sha256": "3741860e59710c05dd625ff4ce8d986c0f8609bae1fab61a230a5790af905c61" | |
| }, | |
| "assessment/robotics_edge_v1/manifest.json": { | |
| "bytes": 1694, | |
| "sha256": "d7e821f637cf81198bd4ef500ff8377159778805cbc40d3230e39626d7728628" | |
| }, | |
| "assessment/robotics_edge_v1/metrics.json": { | |
| "bytes": 14385, | |
| "sha256": "7a7426058007a9168d4c53dfe8a5b4fb8c5e4b54a33e4ce18405421c9877e874" | |
| }, | |
| "assessment/robotics_edge_v1/predictions.jsonl": { | |
| "bytes": 389133, | |
| "sha256": "71cc0ac4c6a6195863a25b2788a21d839415058eeca5cc4a92091487dc496d7b" | |
| }, | |
| "config.json": { | |
| "bytes": 682, | |
| "sha256": "a66629f39ecb44414aefdf78aa947829e37daf6e6a44be8d710e944ec90ef60a" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/REPORT.md": { | |
| "bytes": 6258, | |
| "sha256": "24d19d9788cf7d9e9fe40e856051c6480f1f2be15d62dd407d0c25149be3bd25" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/benchmark.py": { | |
| "bytes": 13816, | |
| "sha256": "2a2a0694235642db38ffdbfe3838d5318224309cb4161b85e33486c1743f2061" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/bundle_manifest.json": { | |
| "bytes": 17568, | |
| "sha256": "29754d52abb0f2201d55819186df85d0df8f733a740d2e128b2830f587027b38" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/cases/poc1_latency.json": { | |
| "bytes": 2180, | |
| "sha256": "157cb10e338b20c09e7c383eb9d5ed1f23984ded1984f32f2d228b65ee8e6700" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/cases/poc1_quality.json": { | |
| "bytes": 193903, | |
| "sha256": "a3e20755d442252731b96f8faff4a9d5b4e4074af130f9b4c9063be5e60504ee" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/environment.lock.txt": { | |
| "bytes": 506, | |
| "sha256": "0dae9933461ff1551edb8afdc7cc89e1b63dacddcd1dcca33d4be07b7e5bd0ba" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/provenance.json": { | |
| "bytes": 9360, | |
| "sha256": "eea82a739be147d4e90fca76d92da40d3f8fc50d7fe11606f49be815f54ad36b" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/readings.csv": { | |
| "bytes": 103401, | |
| "sha256": "1c487fd04aa8f1a608aa2f81f4ca275a7bdc2bd121e0bd2cd72131b39eeae7ff" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/reproduce.py": { | |
| "bytes": 1503, | |
| "sha256": "1fb5bb68f46b02329ecccb66f3de20b301f66e0d41c4eaba53fa7e3224c982ee" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/results/poc1_t1.json": { | |
| "bytes": 542969, | |
| "sha256": "67d94f301dddf46c0899ce9161c1a3ccab66faca9ec08ebc80b874a908f438f6" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/results/poc1_t4.json": { | |
| "bytes": 230245, | |
| "sha256": "afba1ed7e145a64149508e3b7f61264ea0e7a5155acf06ef7cb0a2c91f2af141" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/runtime_identity.json": { | |
| "bytes": 5078, | |
| "sha256": "d5b81efe500eaa4550833a6dd3883e7f9d2a03a9a7e77932386cffcba81b3780" | |
| }, | |
| "edge_benchmarks/rpi5-2026-09-26/temperature_latency.png": { | |
| "bytes": 154941, | |
| "sha256": "b84806634d248d984b85ec0603a61be8ade6b6738c59f7c4c1f2f401b85d586d" | |
| }, | |
| "evaluation/metrics.json": { | |
| "bytes": 10936, | |
| "sha256": "9f53479d2b67bd06fc3a5b56f2dba2856bcb11778cef1fe0afa0e0a39a99d6c9" | |
| }, | |
| "evaluation/raw_diagnostic_predictions.jsonl.gz": { | |
| "bytes": 16504, | |
| "sha256": "dc834114aafc7c28982f8440e2493e59e24cbafa79476a3e00f0d048c33b803f" | |
| }, | |
| "evaluation/test_predictions.jsonl.gz": { | |
| "bytes": 498154, | |
| "sha256": "cfd68ce95dd52db54461812a9c1e61679d693c117576e35b59728f4ef9e8fb01" | |
| }, | |
| "generation_config.json": { | |
| "bytes": 132, | |
| "sha256": "9b962893b09457be3f8b0d343c8d64d33048443e2e57fbe421cd40d2dec8edf9" | |
| }, | |
| "manifest.json": { | |
| "bytes": 12618, | |
| "sha256": "2ead74207a38ad593819da12c52392bad8a273cc62e6842a8278ebffaa561eaa" | |
| }, | |
| "model.safetensors": { | |
| "bytes": 4380048, | |
| "sha256": "7eed2ed8eb5455f4195cba48ff38b2bc8ff8228cefaf7ee6c477200c776a8ea3" | |
| }, | |
| "output_schema.json": { | |
| "bytes": 797, | |
| "sha256": "e5c670db2756306cfb58f43e020426a174aef2f60c643ec0cc72920be4aaae86" | |
| }, | |
| "requirements.txt": { | |
| "bytes": 111, | |
| "sha256": "e565b0c29221c7e17347cdbaeaa7cba2efee571d2ca8f742d4882925705db460" | |
| }, | |
| "special_tokens_map.json": { | |
| "bytes": 531, | |
| "sha256": "eae55585dbdfe3c1875015bd0a96dee1b5103a5ab4ef97797de606fb385ea51d" | |
| }, | |
| "tiny_json_llm/__init__.py": { | |
| "bytes": 103, | |
| "sha256": "e8edab0c5d6fc4202a0b3005dfb4009894ed4c06f216c801943a88f88b7653c2" | |
| }, | |
| "tiny_json_llm/data.py": { | |
| "bytes": 18760, | |
| "sha256": "b1c6dd1207327bc8b9a325391d60762d419589b900ad1329ed21a13df48bc66b" | |
| }, | |
| "tiny_json_llm/evaluate.py": { | |
| "bytes": 6317, | |
| "sha256": "1efd2f862da1fdc6fb17006547de7c53321dbd29aa16c4097daccbfb8dc41e4d" | |
| }, | |
| "tiny_json_llm/infer.py": { | |
| "bytes": 4260, | |
| "sha256": "2b5074bce3f07127fa254c4ec62e25c6b8ce58743b937cdd301d7bb05128a5c8" | |
| }, | |
| "tiny_json_llm/train.py": { | |
| "bytes": 17277, | |
| "sha256": "911848ac7816a1a58bbad171a75e1e5e74a9e2790f18492e69d41e0ec4c8ed2a" | |
| }, | |
| "tokenizer.json": { | |
| "bytes": 54877, | |
| "sha256": "0e2e4281172d6ff20e5562d8e0df4c796ca6c0a9e1804067e1b62bdefe38317e" | |
| }, | |
| "tokenizer_config.json": { | |
| "bytes": 2077, | |
| "sha256": "66e9e99973752a3b3b6adf621fa1574aa576da1fd2f344b8673196de207da9ad" | |
| }, | |
| "training/Tiny_Home_JSON_A100.ipynb": { | |
| "bytes": 61976, | |
| "sha256": "ed056ea07f969f1983b1d5efa98030df5ce72ab571b0369616b3e33b6a5d8365" | |
| }, | |
| "training/audit_dataset.py": { | |
| "bytes": 4051, | |
| "sha256": "687b8c1cfabb9031eb9ddc901de47b4c2115b77d4aa22c6b35912556ae7f9f4e" | |
| }, | |
| "training/build_notebook.py": { | |
| "bytes": 10392, | |
| "sha256": "aed41ec5deed9dd4fc77f94c35a41baec27b0199cfc87d9361568e16811bd1f5" | |
| }, | |
| "training/prepare_home.py": { | |
| "bytes": 11051, | |
| "sha256": "fa2cb809cfb01b3ce4f6dce638167b6666d7a28b72a8755769a11fce4584678b" | |
| }, | |
| "training/run.json": { | |
| "bytes": 1024, | |
| "sha256": "1cafbddca61420914c6435de449af55007fd8ec7cc06ba58b399ffc9a7d113ea" | |
| }, | |
| "training/train_log.jsonl": { | |
| "bytes": 14843, | |
| "sha256": "c371de9912ae1d6e589551685c20735be1ff5177271d375eeb69ba5fc7195075" | |
| }, | |
| "training/verify_pipeline.py": { | |
| "bytes": 3744, | |
| "sha256": "c7a05d4418ad3fbe822ebe3fef1e919c4d52f97ad1ebf1a5cd39a612d75e96f3" | |
| }, | |
| "training_metadata.json": { | |
| "bytes": 1190, | |
| "sha256": "5fd7ee7df81d8699b853cfa2e33ee70b5ff8172ef8de67b11aee54e8cf73d11f" | |
| }, | |
| "verification/downloaded_model_verification.json": { | |
| "bytes": 1218, | |
| "sha256": "eb5a35786c49cf8673cb5a0d77a40a22a133c61032c4fe0537371f10f3efee35" | |
| }, | |
| "verification/release_examples.json": { | |
| "bytes": 477, | |
| "sha256": "fc2bbc5f7b2dd94b74b2f0a876a0f1d1e0908d8c2b5ae3d297d24412fa4ef0a0" | |
| }, | |
| "verification/verification_report.json": { | |
| "bytes": 600, | |
| "sha256": "a6d1c44f033b6a36564d26ee4ccea915aca3007bf503e480dd645e02d4cb2d48" | |
| }, | |
| "weights_sha256.json": { | |
| "bytes": 94, | |
| "sha256": "0d186660bf35658801dea63222e4de0612c237ba13553569535f5b5077824ba1" | |
| } | |
| }, | |
| "documentation_patch": "Repository renamed at the publisher's request; model title, usage and linked dataset references updated. Weights, runtime code and all training/evaluation data are unchanged.", | |
| "previous_release_commit": "89ccd2a58be3831640b13e9e1c63d1234d25ea39", | |
| "renamed_from": "sraivante/tiny-home-json-1m-v1", | |
| "edge_measurement_update": { | |
| "revision": "edge-rpi5-20260926.1", | |
| "date": "2026-09-26", | |
| "weights_and_training_data_changed": false, | |
| "files": "edge_benchmarks/rpi5-2026-09-26" | |
| } | |
| } | |