Text Generation
Transformers
Safetensors
olmo3
math
sft
lora
think
task-vector
iclr2027
conversational
Instructions to use modrill/math-think-o7b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modrill/math-think-o7b-20260908 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="modrill/math-think-o7b-20260908") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("modrill/math-think-o7b-20260908") model = AutoModelForCausalLM.from_pretrained("modrill/math-think-o7b-20260908", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use modrill/math-think-o7b-20260908 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "modrill/math-think-o7b-20260908" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/math-think-o7b-20260908", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/modrill/math-think-o7b-20260908
- SGLang
How to use modrill/math-think-o7b-20260908 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 "modrill/math-think-o7b-20260908" \ --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": "modrill/math-think-o7b-20260908", "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 "modrill/math-think-o7b-20260908" \ --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": "modrill/math-think-o7b-20260908", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use modrill/math-think-o7b-20260908 with Docker Model Runner:
docker model run hf.co/modrill/math-think-o7b-20260908
| { | |
| "schema": "ddc-atomic-checkpoint-commit/1", | |
| "runner_id": "THINK_B_2EP_SIX_ARMS_RUNNER_V3", | |
| "completed_optimizer_updates": 987, | |
| "cumulative_realized_active_tokens": 64632872, | |
| "bindings": { | |
| "config_sha256": "5c5965a584fe72804b4752efb2e27b010079eb50e0357eb288923d913e458fa4", | |
| "runner_code_sha256": "fd6d1c6403810acc4460e2ce0fb5f4418881387b11f4bd21f7cd21067faa3a0a", | |
| "config_schema_sha256": "d6d13eeee42bf04cf34fc68b2fa7a61b316c4543b77d7d779815b8eddf10c099", | |
| "python_binary_sha256": "5700a6a7804feb44da6c963ebd1323982478b7ca57478e4e81981c47818453bd", | |
| "environment_lock_sha256": "627d4fe088b8f64841b0520ae5bd9dc5c81e9dcd5969b4bd45c9a9910b2f3c01", | |
| "base_composite_sha256": "526963d72561cb6244f60f751312673d2671111d214636ae571de0d62c762760", | |
| "base_lock_sha256": "6791648e4030008388f2e9241b23771cb07eb0416fbd7bc3c6777c7c36bda3be", | |
| "frozen_rows_sha256": "8221ff30de8fa345441e6002c111c948a3fdd20413e5c09e3a8f76cf26b12ef1", | |
| "ordered_ids_sha256": "dde87a60437027a3e19566382b4ac25381f2888e45507bef0ddc3d6d284c412b", | |
| "update_plan_sha256": "24e1f6fecc9e9e5b5c371c7041cbe0bf79dec48741caf8a60d50310984e59ef1", | |
| "data_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", | |
| "decontamination_receipt_sha256": "66c360871b06208ed20e473e57ad0f09c79e4dac1b3124a9461a5b729b487153", | |
| "render_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", | |
| "token_bake_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b", | |
| "continuation_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b" | |
| }, | |
| "trainer_state": { | |
| "path": "trainer_state.pt", | |
| "bytes": 1919557677, | |
| "sha256": "1ecc81d3f7ee1f1acffd3a9cba3ccf42de56b7bc476571a1b928dee3d2d7058b" | |
| }, | |
| "token_boundary_ledger": { | |
| "path": "TOKEN_BOUNDARY_LEDGER.json", | |
| "bytes": 970601, | |
| "sha256": "bbf8fc19c70dc5bab6b95bfd8799a022599968157ab72f4e3dc0c1f196e74a4b" | |
| }, | |
| "adapter_files": [ | |
| { | |
| "path": "adapter/README.md", | |
| "bytes": 5282, | |
| "sha256": "45145483fe203512c1f26bd8675f16875cc326c7cfe5e3020cdf0f50f297acf2" | |
| }, | |
| { | |
| "path": "adapter/adapter_config.json", | |
| "bytes": 1276, | |
| "sha256": "b0b7fe4369c25edd35ad553eb42a78160c4317ba719fbc1ece7cf824dae037bb" | |
| }, | |
| { | |
| "path": "adapter/adapter_model.safetensors", | |
| "bytes": 639724904, | |
| "sha256": "9da5899df6a1d6d7cfb9e412085eed9a85693bd0fd848645b176e34deed0d8e2" | |
| } | |
| ], | |
| "serialization_canary": { | |
| "save_load_format": "safetensors", | |
| "state_key_count": 450, | |
| "token_state": { | |
| "schema": "think-b-2ep-token-rows/1", | |
| "tensors": [ | |
| { | |
| "key": "base_model.model.lm_head.token_adapter.trainable_tokens_delta", | |
| "sha256": "037ef35dc1d9a3f53df04a14fc8f4c259ae071ac569f124410b850e091ada551", | |
| "shape": [ | |
| 1, | |
| 4096 | |
| ], | |
| "dtype": "torch.float32" | |
| }, | |
| { | |
| "key": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta", | |
| "sha256": "1f1a38b5c91a31be7cc7cd0f4dded40c8cb9781f2ceaefda73c2eb5e2d52e899", | |
| "shape": [ | |
| 1, | |
| 4096 | |
| ], | |
| "dtype": "torch.float32" | |
| } | |
| ] | |
| } | |
| }, | |
| "token_state": { | |
| "schema": "think-b-2ep-token-rows/1", | |
| "tensors": [ | |
| { | |
| "key": "base_model.model.lm_head.token_adapter.trainable_tokens_delta", | |
| "sha256": "037ef35dc1d9a3f53df04a14fc8f4c259ae071ac569f124410b850e091ada551", | |
| "shape": [ | |
| 1, | |
| 4096 | |
| ], | |
| "dtype": "torch.float32" | |
| }, | |
| { | |
| "key": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta", | |
| "sha256": "1f1a38b5c91a31be7cc7cd0f4dded40c8cb9781f2ceaefda73c2eb5e2d52e899", | |
| "shape": [ | |
| 1, | |
| 4096 | |
| ], | |
| "dtype": "torch.float32" | |
| } | |
| ] | |
| } | |
| } | |