Text Generation
Transformers
Safetensors
English
microloop_diffusion
causal-lm
base-model
small-language-model
custom_code
muon
hummingbird-v1
conversational
Instructions to use juinron/Hummingbird-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use juinron/Hummingbird-V1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="juinron/Hummingbird-V1", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("juinron/Hummingbird-V1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use juinron/Hummingbird-V1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "juinron/Hummingbird-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": "juinron/Hummingbird-V1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/juinron/Hummingbird-V1
- SGLang
How to use juinron/Hummingbird-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 "juinron/Hummingbird-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": "juinron/Hummingbird-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 "juinron/Hummingbird-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": "juinron/Hummingbird-V1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use juinron/Hummingbird-V1 with Docker Model Runner:
docker model run hf.co/juinron/Hummingbird-V1
| { | |
| "acc": 36.1, | |
| "acc_norm": 36.1, | |
| "categories": { | |
| "elementary_school_math_continuation::addition::grades_1_2::easy": { | |
| "acc": 26.5625, | |
| "acc_norm": 26.5625, | |
| "norm_correct": 34, | |
| "raw_correct": 34, | |
| "total": 128 | |
| }, | |
| "elementary_school_math_continuation::comparison::grades_2_3::medium": { | |
| "acc": 15.909090909090908, | |
| "acc_norm": 15.909090909090908, | |
| "norm_correct": 7, | |
| "raw_correct": 7, | |
| "total": 44 | |
| }, | |
| "elementary_school_math_continuation::comparison_difference::grades_2_3::medium": { | |
| "acc": 37.5, | |
| "acc_norm": 37.5, | |
| "norm_correct": 18, | |
| "raw_correct": 18, | |
| "total": 48 | |
| }, | |
| "elementary_school_math_continuation::data::grades_2_3::easy": { | |
| "acc": 27.906976744186046, | |
| "acc_norm": 27.906976744186046, | |
| "norm_correct": 12, | |
| "raw_correct": 12, | |
| "total": 43 | |
| }, | |
| "elementary_school_math_continuation::division::grades_3_4::medium": { | |
| "acc": 37.03703703703704, | |
| "acc_norm": 37.03703703703704, | |
| "norm_correct": 20, | |
| "raw_correct": 20, | |
| "total": 54 | |
| }, | |
| "elementary_school_math_continuation::fractions_counting::grades_3_4::medium": { | |
| "acc": 24.0, | |
| "acc_norm": 26.0, | |
| "norm_correct": 13, | |
| "raw_correct": 12, | |
| "total": 50 | |
| }, | |
| "elementary_school_math_continuation::geometry_area::grades_4_5::medium": { | |
| "acc": 53.84615384615385, | |
| "acc_norm": 53.84615384615385, | |
| "norm_correct": 28, | |
| "raw_correct": 28, | |
| "total": 52 | |
| }, | |
| "elementary_school_math_continuation::geometry_perimeter::grades_4_5::medium": { | |
| "acc": 46.666666666666664, | |
| "acc_norm": 46.666666666666664, | |
| "norm_correct": 21, | |
| "raw_correct": 21, | |
| "total": 45 | |
| }, | |
| "elementary_school_math_continuation::measurement::grades_2_3::easy": { | |
| "acc": 36.84210526315789, | |
| "acc_norm": 36.84210526315789, | |
| "norm_correct": 28, | |
| "raw_correct": 28, | |
| "total": 76 | |
| }, | |
| "elementary_school_math_continuation::money::grades_3_4::medium": { | |
| "acc": 32.8125, | |
| "acc_norm": 32.8125, | |
| "norm_correct": 21, | |
| "raw_correct": 21, | |
| "total": 64 | |
| }, | |
| "elementary_school_math_continuation::multiplication::grades_3_4::medium": { | |
| "acc": 44.5945945945946, | |
| "acc_norm": 44.5945945945946, | |
| "norm_correct": 33, | |
| "raw_correct": 33, | |
| "total": 74 | |
| }, | |
| "elementary_school_math_continuation::patterns::grades_3_4::medium": { | |
| "acc": 28.30188679245283, | |
| "acc_norm": 28.30188679245283, | |
| "norm_correct": 15, | |
| "raw_correct": 15, | |
| "total": 53 | |
| }, | |
| "elementary_school_math_continuation::subtraction::grades_1_2::easy": { | |
| "acc": 26.495726495726498, | |
| "acc_norm": 25.64102564102564, | |
| "norm_correct": 30, | |
| "raw_correct": 31, | |
| "total": 117 | |
| }, | |
| "elementary_school_math_continuation::time::grades_2_3::easy": { | |
| "acc": 92.72727272727272, | |
| "acc_norm": 92.72727272727272, | |
| "norm_correct": 51, | |
| "raw_correct": 51, | |
| "total": 55 | |
| }, | |
| "elementary_school_math_continuation::two_step_add_subtract::grades_2_3::medium": { | |
| "acc": 26.08695652173913, | |
| "acc_norm": 26.08695652173913, | |
| "norm_correct": 12, | |
| "raw_correct": 12, | |
| "total": 46 | |
| }, | |
| "elementary_school_math_continuation::two_step_addition::grades_2_3::medium": { | |
| "acc": 42.10526315789473, | |
| "acc_norm": 42.10526315789473, | |
| "norm_correct": 8, | |
| "raw_correct": 8, | |
| "total": 19 | |
| }, | |
| "elementary_school_math_continuation::two_step_subtraction::grades_2_3::medium": { | |
| "acc": 31.25, | |
| "acc_norm": 31.25, | |
| "norm_correct": 10, | |
| "raw_correct": 10, | |
| "total": 32 | |
| } | |
| }, | |
| "frost_evaluation": { | |
| "checkpoint": "D:\\llm\\frost\\artifacts\\runs\\natural20b_pilot_muon_b32\\checkpoint-tokens-0500000000", | |
| "data_sha256": "bf8ab1a5193d52cdf0e05ff0b3ca226bdfcf416cb6e75562dcbe72e7e4559435", | |
| "dataset": "AxiomicLabs/Arithmark-3.0", | |
| "dataset_revision": "6f6e59dd9b7e2c63455f7af7f838f9ecc3d0a746", | |
| "device": "cuda", | |
| "evaluator_sha256": "09667e1ea05ecd8b91dbfea14a47365b555c72622afed9fc284c127ecd5e1bcd", | |
| "limit": null, | |
| "precision": "bfloat16", | |
| "tokenizer": "D:\\llm\\frost\\artifacts\\runs\\e3_tokenizers\\tok_4k_digit" | |
| }, | |
| "norm_correct": 361, | |
| "raw_correct": 361, | |
| "timing": { | |
| "evaluation_seconds": 1.190516500002559, | |
| "examples_per_second": 839.9715585612215, | |
| "tokenization_seconds": 0.3197372000031464 | |
| }, | |
| "total": 1000 | |
| } |