Text Generation
Transformers
Safetensors
English
smollm3
education
english-tutor
structured-output
experimental
merged
conversational
Instructions to use sraivante/TARA-English-Tutor-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sraivante/TARA-English-Tutor-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sraivante/TARA-English-Tutor-3B") 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/TARA-English-Tutor-3B") model = AutoModelForCausalLM.from_pretrained("sraivante/TARA-English-Tutor-3B", 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/TARA-English-Tutor-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sraivante/TARA-English-Tutor-3B" # 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/TARA-English-Tutor-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sraivante/TARA-English-Tutor-3B
- SGLang
How to use sraivante/TARA-English-Tutor-3B 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/TARA-English-Tutor-3B" \ --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/TARA-English-Tutor-3B", "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/TARA-English-Tutor-3B" \ --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/TARA-English-Tutor-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use sraivante/TARA-English-Tutor-3B with Docker Model Runner:
docker model run hf.co/sraivante/TARA-English-Tutor-3B
Download training_data/provenance.json from sraivante/TARA-English-Tutor-3B: direct link, hf CLI and curl.
- Browser
- Download file 6.43 kB
-
https://huggingface.co/sraivante/TARA-English-Tutor-3B/resolve/main/training_data/provenance.json
- Command line
-
hf download hf://sraivante/TARA-English-Tutor-3B/training_data/provenance.json
-
curl -L -o provenance.json https://huggingface.co/sraivante/TARA-English-Tutor-3B/resolve/main/training_data/provenance.json
6.43 kB
| { | |
| "dataset": "TARA English Tutor Instructions", | |
| "publisher": "sraivante", | |
| "source_project": "CUSTOM_LLM4", | |
| "copyright": "Copyright (c) 2026 sraivante; original authored dataset content and selection/arrangement.", | |
| "license": "Apache-2.0", | |
| "source_code_license": "MIT; original notice retained in SOURCE_LICENSE_MIT", | |
| "original_content_declared": true, | |
| "teacher_reviewed": false, | |
| "source_generation": { | |
| "concept_records": 54, | |
| "method": "Deterministic original curriculum templates plus fixed help-seeking examples, eight grade profiles, five question variants and encouraging responses.", | |
| "seed": 42, | |
| "validation_fraction_requested": 0.1, | |
| "split_policy": "SHA256 of seed and group_id assigns all paraphrases of a concept to one split.", | |
| "third_party_textbook_passages_in_source": false | |
| }, | |
| "files": { | |
| "train": { | |
| "path": "data/train.jsonl", | |
| "records": 1138, | |
| "bytes": 2651491, | |
| "sha256": "33a9949ef2e43f97581ba6e371007298027c35c4266924c40a5dc8c3dc25ada0" | |
| }, | |
| "validation": { | |
| "path": "data/validation.jsonl", | |
| "records": 126, | |
| "bytes": 288892, | |
| "sha256": "dc1d73be7d960fa952303951aac2ed45b1068e3aeda17c2a28b8a0407fd6a47f" | |
| } | |
| }, | |
| "model_repository": "sraivante/TARA-English-Tutor-3B", | |
| "model_association": { | |
| "original_colab_bundle_sha256": "c2466fe27b2fc0ac53759417eb84d98530b8b4617a6c2f1d65761aeb777e36c3", | |
| "original_training_workflow_notebook_sha256": "95da45fc499b086b18956079eb2f725f3a8f58f50d82064bd02ce6504e5f27c3", | |
| "original_bundle_reproduces_current_data_byte_for_byte": true, | |
| "local_generation_reproduces_current_data_byte_for_byte": true, | |
| "original_training_run_dataset_hashes_available": false, | |
| "original_training_manifest_available": false, | |
| "historical_identity_note": "The published files exactly reproduce the original Colab bundle's deterministic build. No saved dataset hash from the actual Colab training run was available, so byte-for-byte historical identity with that run cannot independently be proven." | |
| }, | |
| "audit": { | |
| "schema_errors": 0, | |
| "vocabulary_warning_rows": 0, | |
| "duplicate_message_records": 0, | |
| "overlap": { | |
| "ids": 0, | |
| "groups": 0, | |
| "messages": 0, | |
| "user_prompts": 0 | |
| }, | |
| "teacher_reviewed_records": 0 | |
| }, | |
| "source_files": { | |
| "LICENSE": { | |
| "sha256": "4d0003131a2e906712f371183385028862931c49f3b017ad61777dbca45287b9", | |
| "bytes": 1084 | |
| }, | |
| "configs/training.json": { | |
| "sha256": "dac226782acb193f78197c02c202db37bdf462b2a06560758c85dbfae2637bd9", | |
| "bytes": 654 | |
| }, | |
| "scripts/audit_dataset.py": { | |
| "sha256": "372b4dc1ad4b5d755405925f01c83e9ad8fda78e08714309997a0b48f24fbd07", | |
| "bytes": 1705 | |
| }, | |
| "scripts/evaluate_adapter.py": { | |
| "sha256": "cb1cb023c0148bb03d01f48ec8a03107366641063a8827dd52cad2b79e120818", | |
| "bytes": 4029 | |
| }, | |
| "scripts/export_review_sheet.py": { | |
| "sha256": "766608a288233474a2fcc9e054bb5735e894917e51577b9eb56f6fa27c6b064f", | |
| "bytes": 2448 | |
| }, | |
| "scripts/merge_adapter.py": { | |
| "sha256": "6ec7bfff5c7e7b48eabc367bb97a37952ee22243938fdc0a89b0a8b70b901258", | |
| "bytes": 1669 | |
| }, | |
| "scripts/train_qlora.py": { | |
| "sha256": "23bfac854b149180e7047858ee983f95133300148fa937bd13dcd3c464fea89f", | |
| "bytes": 10982 | |
| }, | |
| "src/cbse_tutor/__init__.py": { | |
| "sha256": "d4af2f36b89b5bd04da2912b8073115871010b2b4ecd7de10978ca90ba74891c", | |
| "bytes": 253 | |
| }, | |
| "src/cbse_tutor/curriculum.py": { | |
| "sha256": "19ddb98f3b143998186ff08e87c0db0fb903f9bc262dcd8e2d09a6f212223900", | |
| "bytes": 2766 | |
| }, | |
| "src/cbse_tutor/dataset.py": { | |
| "sha256": "b344672f2c245212ccbb58c077f26917cad3c7a05bf8ac92be10c801975fab22", | |
| "bytes": 10945 | |
| }, | |
| "src/cbse_tutor/engine.py": { | |
| "sha256": "110ac5b41bb2de2528e4fbceb7e78e020441f4cbc14fad84b562f5329b095870", | |
| "bytes": 11942 | |
| }, | |
| "src/cbse_tutor/profiles.py": { | |
| "sha256": "930f2bd43bb48fe41762f0f3157b57961841028dc299c01a092fd89a6331da56", | |
| "bytes": 6073 | |
| }, | |
| "src/cbse_tutor/prompting.py": { | |
| "sha256": "0048539e643945efa86d4c09f7e30f481590c3801b15dadd73c8275d55cbf406", | |
| "bytes": 3421 | |
| }, | |
| "src/cbse_tutor/resources/concepts.json": { | |
| "sha256": "f6c9d307ff0e0929da152caf3ed9615d2986878144d4ed592f5f19575737fcda", | |
| "bytes": 33698 | |
| }, | |
| "src/cbse_tutor/resources/eval_prompts.json": { | |
| "sha256": "5e393efab6b91fe0398ff9728b0bfee44d4ce0b714f63b6a44d6a1572c09313f", | |
| "bytes": 2987 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_0.txt": { | |
| "sha256": "b63a8f590698e7e92632f7624582066010261bf8a3c6a7fb3f027d9b368e224c", | |
| "bytes": 1289 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_1.txt": { | |
| "sha256": "4ec6e1fcfdcfb1078ae26e15cc28e75c10cd707a75b8372d4ffebc22f4907a54", | |
| "bytes": 545 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_2.txt": { | |
| "sha256": "3e185c05f5792c3678f3e0f08b5dfd695bb4e7ba636464cab418f3a40dec533e", | |
| "bytes": 542 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_3.txt": { | |
| "sha256": "dec57de4a1b94eb1aa1142c35ddd5699fed8e132e888ca6d582e0def6ed52e0f", | |
| "bytes": 662 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_4.txt": { | |
| "sha256": "f70cf7657564c0cbc72b35d60f39ce5fa48c706b340a72a94f1489e3fd5beff7", | |
| "bytes": 624 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_5.txt": { | |
| "sha256": "77313a786f9628624f38c12a45b69675b27b2fa2e8470c3ec26215917e50fbf9", | |
| "bytes": 638 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_6.txt": { | |
| "sha256": "413d6796d7efbd714fcecfd8c6129997e124e3d5b7dc92a3162922ef95d99062", | |
| "bytes": 553 | |
| }, | |
| "src/cbse_tutor/resources/vocabulary/tier_7.txt": { | |
| "sha256": "8775b549727d73fc1e9d012488b35aad8c4e4cf884f6cd9e31741e5f63f9bc2a", | |
| "bytes": 606 | |
| }, | |
| "src/cbse_tutor/safety.py": { | |
| "sha256": "266344f7c281ae7d009052f24de83706d494b8113d0ddfb6c28c5fee3567a7c8", | |
| "bytes": 7208 | |
| }, | |
| "src/cbse_tutor/schemas.py": { | |
| "sha256": "139dd4d217fed2b122e35133be6bf408ab2fc86e34cde2c62bf77531580b5f34", | |
| "bytes": 2114 | |
| }, | |
| "src/cbse_tutor/vocabulary.py": { | |
| "sha256": "e6df15fa5fcfb0825e6c77ff21c400aa2a07e49613bf5bfa334ad88729a90e65", | |
| "bytes": 7875 | |
| } | |
| }, | |
| "scope": "The separate 300M scratch checkpoint and its pretraining corpora are not part of this 3B fine-tune." | |
| } | |