Text Generation
Transformers
Safetensors
qwen3
Merge
taskvector
math
nothink
conversational
text-generation-inference
Instructions to use Montalte/qwen4b-math-nothink-taskvector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Montalte/qwen4b-math-nothink-taskvector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Montalte/qwen4b-math-nothink-taskvector") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Montalte/qwen4b-math-nothink-taskvector") model = AutoModelForCausalLM.from_pretrained("Montalte/qwen4b-math-nothink-taskvector", 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 Montalte/qwen4b-math-nothink-taskvector with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Montalte/qwen4b-math-nothink-taskvector" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Montalte/qwen4b-math-nothink-taskvector", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Montalte/qwen4b-math-nothink-taskvector
- SGLang
How to use Montalte/qwen4b-math-nothink-taskvector 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 "Montalte/qwen4b-math-nothink-taskvector" \ --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": "Montalte/qwen4b-math-nothink-taskvector", "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 "Montalte/qwen4b-math-nothink-taskvector" \ --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": "Montalte/qwen4b-math-nothink-taskvector", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Montalte/qwen4b-math-nothink-taskvector with Docker Model Runner:
docker model run hf.co/Montalte/qwen4b-math-nothink-taskvector
Download COMMIT.json from Montalte/qwen4b-math-nothink-taskvector: direct link, hf CLI and curl.
- Browser
- Download file 3.93 kB
-
https://huggingface.co/Montalte/qwen4b-math-nothink-taskvector/resolve/main/COMMIT.json
- Command line
-
hf download hf://Montalte/qwen4b-math-nothink-taskvector/COMMIT.json
-
curl -L -o COMMIT.json https://huggingface.co/Montalte/qwen4b-math-nothink-taskvector/resolve/main/COMMIT.json
3.93 kB
| { | |
| "schema": "ddc-atomic-checkpoint-commit/1", | |
| "runner_id": "THINK_B_2EP_SIX_ARMS_RUNNER_V3", | |
| "completed_optimizer_updates": 165, | |
| "cumulative_realized_active_tokens": 10788766, | |
| "bindings": { | |
| "config_sha256": "ed1535bfd150f0cf7f117d9268aed978a2171136d03cd7289923b775e136e4f5", | |
| "runner_code_sha256": "fd6d1c6403810acc4460e2ce0fb5f4418881387b11f4bd21f7cd21067faa3a0a", | |
| "config_schema_sha256": "d6d13eeee42bf04cf34fc68b2fa7a61b316c4543b77d7d779815b8eddf10c099", | |
| "python_binary_sha256": "5700a6a7804feb44da6c963ebd1323982478b7ca57478e4e81981c47818453bd", | |
| "environment_lock_sha256": "627d4fe088b8f64841b0520ae5bd9dc5c81e9dcd5969b4bd45c9a9910b2f3c01", | |
| "base_composite_sha256": "26cbdb468ced4891fee1fffa2be7b7722e5d8d836d0bc986eecd97fa12cd1747", | |
| "base_lock_sha256": "9a145eebf5d9df466a5f554c4850290be671acd284e0f703b7dfdb087555858b", | |
| "frozen_rows_sha256": "1a99ada6e2afb71bf5b7a7af45422104b5e4745e6601a4081ad462473cebe804", | |
| "ordered_ids_sha256": "0152bfafdb38a00d960507db14293e4ff02830745fd63587320e6990a9b5b51f", | |
| "update_plan_sha256": "b16e590277206f95b60c22e04883dc80fe66e93201a39d09cc1e7feb5ca110e6", | |
| "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": 1586261581, | |
| "sha256": "bd68b7d8af1790dcac8b77cf9b221b71d18a7f11661b3046dd37128d679ae5e3" | |
| }, | |
| "token_boundary_ledger": { | |
| "path": "TOKEN_BOUNDARY_LEDGER.json", | |
| "bytes": 247058, | |
| "sha256": "ce83014e2a6589253dd77c9b5da9a8978e6103dda4c8fe88504c7cee20fd7525" | |
| }, | |
| "adapter_files": [ | |
| { | |
| "path": "adapter/README.md", | |
| "bytes": 5414, | |
| "sha256": "5480222f959c7f360c56310c9bfb8de0acfb45aa67a64c1bc9cafa38a7662226" | |
| }, | |
| { | |
| "path": "adapter/adapter_config.json", | |
| "bytes": 1398, | |
| "sha256": "0068dabe8ec044031a9bdb94d05a4675f887f858497c896923da7d4c45812914" | |
| }, | |
| { | |
| "path": "adapter/adapter_model.safetensors", | |
| "bytes": 528611960, | |
| "sha256": "b6e1a5fe40eb2407880953e746ce4788af62034ee395918c4fee179c8770bf54" | |
| } | |
| ], | |
| "serialization_canary": { | |
| "save_load_format": "safetensors", | |
| "state_key_count": 506, | |
| "token_state": { | |
| "schema": "think-b-2ep-token-rows/1", | |
| "tensors": [ | |
| { | |
| "key": "base_model.model.lm_head.token_adapter.trainable_tokens_delta", | |
| "sha256": "5894b8472ed27dbdb63d777758c8bb49a29fd2929921fd5ffc8356e2c8f94e34", | |
| "shape": [ | |
| 3, | |
| 2560 | |
| ], | |
| "dtype": "torch.float32" | |
| }, | |
| { | |
| "key": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta", | |
| "sha256": "98bb98fa6ca4c9be9088716f6b3443e5e2dc6a51dea02de95675341d941460b7", | |
| "shape": [ | |
| 3, | |
| 2560 | |
| ], | |
| "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": "5894b8472ed27dbdb63d777758c8bb49a29fd2929921fd5ffc8356e2c8f94e34", | |
| "shape": [ | |
| 3, | |
| 2560 | |
| ], | |
| "dtype": "torch.float32" | |
| }, | |
| { | |
| "key": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta", | |
| "sha256": "98bb98fa6ca4c9be9088716f6b3443e5e2dc6a51dea02de95675341d941460b7", | |
| "shape": [ | |
| 3, | |
| 2560 | |
| ], | |
| "dtype": "torch.float32" | |
| } | |
| ] | |
| } | |
| } | |