Text Generation
Transformers
Safetensors
PyTorch
cma
custom_code
causal-lm
small-language-model
generalist
4k-tokenizer
Instructions to use User01110/cma-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use User01110/cma-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="User01110/cma-mini", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("User01110/cma-mini", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use User01110/cma-mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "User01110/cma-mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "User01110/cma-mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/User01110/cma-mini
- SGLang
How to use User01110/cma-mini 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 "User01110/cma-mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "User01110/cma-mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "User01110/cma-mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "User01110/cma-mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use User01110/cma-mini with Docker Model Runner:
docker model run hf.co/User01110/cma-mini
| { | |
| "step": 60000, | |
| "parameters": 5094112, | |
| "lm_eval_version": "0.4.12", | |
| "evaluation_dtype": "bfloat16", | |
| "softmax_dtype": "float32", | |
| "evaluation_autocast": false, | |
| "num_fewshot": 0, | |
| "model_context": 1024, | |
| "training_context": 1024, | |
| "lm_eval_context": 1024, | |
| "lm_eval_bos_prefix": true, | |
| "arithmark_3.0_bos_prefix": true, | |
| "benchmark_accuracy": { | |
| "arc_easy": 0.335016835016835, | |
| "arc_challenge": 0.22696245733788395, | |
| "hellaswag": 0.2786297550288787, | |
| "piqa": 0.5729053318824809 | |
| }, | |
| "lm_eval_metric_policy": "acc_norm when available, otherwise acc", | |
| "intelligence_index": 6.837530558172039, | |
| "average_accuracy_percent": 35.26311832721798, | |
| "open_slm_scores": { | |
| "leaderboard": "AxiomicLabs/Open_SLM_Leaderboard", | |
| "leaderboard_revision": "2fbaaa164009c6c0d201ddf245878f5942cc8628", | |
| "intelligence_index": 6.837530558172039, | |
| "average_accuracy_percent": 35.26311832721798, | |
| "components_percent": { | |
| "hellaswag": 27.86297550288787, | |
| "combined_arc": 28.09896461773595, | |
| "piqa": 57.29053318824809, | |
| "arithmark_3.0": 27.800000000000004 | |
| }, | |
| "chance_normalized_components": { | |
| "hellaswag": 3.8173006705171613, | |
| "combined_arc": 4.13195282364793, | |
| "piqa": 14.581066376496183, | |
| "arithmark_3.0": 3.7333333333333396 | |
| }, | |
| "intelligence_index_weights": { | |
| "hellaswag": 1.0, | |
| "combined_arc": 1.0, | |
| "piqa": 1.0, | |
| "arithmark_3.0": 0.65 | |
| } | |
| }, | |
| "checkpoint_policy": "every completed evaluation is committed regardless of whether validation BPB is best; rolling full-precision model, optimizer, RNG, stream cursor, and prefetched batches are stored separately", | |
| "best_tracking_metric": "validation.normalized_bpb@1024 (lower is better)", | |
| "best_validation": { | |
| "normalized_bpb": 1.4126762791486454, | |
| "step": 60000 | |
| }, | |
| "arithmark_3.0": { | |
| "dataset": "AxiomicLabs/Arithmark-3.0", | |
| "dataset_revision": "6f6e59dd9b7e2c63455f7af7f838f9ecc3d0a746", | |
| "primary_metric": "acc_norm", | |
| "metric_unit": "fraction", | |
| "acc": 0.317, | |
| "acc_norm": 0.278, | |
| "raw_correct": 317, | |
| "normalized_correct": 278, | |
| "total": 1000, | |
| "max_context": 1024, | |
| "by_category": { | |
| "elementary_school_math_continuation::addition::grades_1_2::easy": { | |
| "acc": 0.21875, | |
| "acc_norm": 0.21875, | |
| "raw_correct": 28, | |
| "normalized_correct": 28, | |
| "total": 128 | |
| }, | |
| "elementary_school_math_continuation::comparison::grades_2_3::medium": { | |
| "acc": 0.18181818181818182, | |
| "acc_norm": 0.20454545454545456, | |
| "raw_correct": 8, | |
| "normalized_correct": 9, | |
| "total": 44 | |
| }, | |
| "elementary_school_math_continuation::comparison_difference::grades_2_3::medium": { | |
| "acc": 0.16666666666666666, | |
| "acc_norm": 0.14583333333333334, | |
| "raw_correct": 8, | |
| "normalized_correct": 7, | |
| "total": 48 | |
| }, | |
| "elementary_school_math_continuation::data::grades_2_3::easy": { | |
| "acc": 0.18604651162790697, | |
| "acc_norm": 0.18604651162790697, | |
| "raw_correct": 8, | |
| "normalized_correct": 8, | |
| "total": 43 | |
| }, | |
| "elementary_school_math_continuation::division::grades_3_4::medium": { | |
| "acc": 0.3888888888888889, | |
| "acc_norm": 0.3888888888888889, | |
| "raw_correct": 21, | |
| "normalized_correct": 21, | |
| "total": 54 | |
| }, | |
| "elementary_school_math_continuation::fractions_counting::grades_3_4::medium": { | |
| "acc": 0.22, | |
| "acc_norm": 0.22, | |
| "raw_correct": 11, | |
| "normalized_correct": 11, | |
| "total": 50 | |
| }, | |
| "elementary_school_math_continuation::geometry_area::grades_4_5::medium": { | |
| "acc": 0.46153846153846156, | |
| "acc_norm": 0.40384615384615385, | |
| "raw_correct": 24, | |
| "normalized_correct": 21, | |
| "total": 52 | |
| }, | |
| "elementary_school_math_continuation::geometry_perimeter::grades_4_5::medium": { | |
| "acc": 0.5333333333333333, | |
| "acc_norm": 0.5333333333333333, | |
| "raw_correct": 24, | |
| "normalized_correct": 24, | |
| "total": 45 | |
| }, | |
| "elementary_school_math_continuation::measurement::grades_2_3::easy": { | |
| "acc": 0.34210526315789475, | |
| "acc_norm": 0.2894736842105263, | |
| "raw_correct": 26, | |
| "normalized_correct": 22, | |
| "total": 76 | |
| }, | |
| "elementary_school_math_continuation::money::grades_3_4::medium": { | |
| "acc": 0.265625, | |
| "acc_norm": 0.234375, | |
| "raw_correct": 17, | |
| "normalized_correct": 15, | |
| "total": 64 | |
| }, | |
| "elementary_school_math_continuation::multiplication::grades_3_4::medium": { | |
| "acc": 0.36486486486486486, | |
| "acc_norm": 0.3108108108108108, | |
| "raw_correct": 27, | |
| "normalized_correct": 23, | |
| "total": 74 | |
| }, | |
| "elementary_school_math_continuation::patterns::grades_3_4::medium": { | |
| "acc": 0.18867924528301888, | |
| "acc_norm": 0.1509433962264151, | |
| "raw_correct": 10, | |
| "normalized_correct": 8, | |
| "total": 53 | |
| }, | |
| "elementary_school_math_continuation::subtraction::grades_1_2::easy": { | |
| "acc": 0.2222222222222222, | |
| "acc_norm": 0.18803418803418803, | |
| "raw_correct": 26, | |
| "normalized_correct": 22, | |
| "total": 117 | |
| }, | |
| "elementary_school_math_continuation::time::grades_2_3::easy": { | |
| "acc": 1.0, | |
| "acc_norm": 0.6363636363636364, | |
| "raw_correct": 55, | |
| "normalized_correct": 35, | |
| "total": 55 | |
| }, | |
| "elementary_school_math_continuation::two_step_add_subtract::grades_2_3::medium": { | |
| "acc": 0.2391304347826087, | |
| "acc_norm": 0.2391304347826087, | |
| "raw_correct": 11, | |
| "normalized_correct": 11, | |
| "total": 46 | |
| }, | |
| "elementary_school_math_continuation::two_step_addition::grades_2_3::medium": { | |
| "acc": 0.21052631578947367, | |
| "acc_norm": 0.21052631578947367, | |
| "raw_correct": 4, | |
| "normalized_correct": 4, | |
| "total": 19 | |
| }, | |
| "elementary_school_math_continuation::two_step_subtraction::grades_2_3::medium": { | |
| "acc": 0.28125, | |
| "acc_norm": 0.28125, | |
| "raw_correct": 9, | |
| "normalized_correct": 9, | |
| "total": 32 | |
| } | |
| }, | |
| "choice_batch_size": 64 | |
| }, | |
| "validation": { | |
| "loss": 3.124341521462218, | |
| "perplexity": 22.744913124279417, | |
| "normalized_bpb": 1.4126762791486454, | |
| "tokens": 359037, | |
| "normalized_utf8_bytes": 1145591, | |
| "window": 1024, | |
| "stride": 512 | |
| } | |
| } |