Text Generation
Transformers
Safetensors
PyTorch
English
modern_dense_mha_gated_ffn_router
custom_code
causal-lm
small-language-model
babylm
strict-small
swiglu
research
Instructions to use AwakeningOS/VISTA-24M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AwakeningOS/VISTA-24M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AwakeningOS/VISTA-24M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AwakeningOS/VISTA-24M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AwakeningOS/VISTA-24M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AwakeningOS/VISTA-24M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AwakeningOS/VISTA-24M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AwakeningOS/VISTA-24M
- SGLang
How to use AwakeningOS/VISTA-24M 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 "AwakeningOS/VISTA-24M" \ --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": "AwakeningOS/VISTA-24M", "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 "AwakeningOS/VISTA-24M" \ --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": "AwakeningOS/VISTA-24M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AwakeningOS/VISTA-24M with Docker Model Runner:
docker model run hf.co/AwakeningOS/VISTA-24M
Release VISTA-24M: model, architecture diagrams, training recipe and evaluation evidence
9287d39 verified Download evaluation/learning_curve.json from AwakeningOS/VISTA-24M: direct link, hf CLI and curl.
- Browser
- Download file 2.79 kB
-
https://huggingface.co/AwakeningOS/VISTA-24M/resolve/main/evaluation/learning_curve.json
- Command line
-
hf download hf://AwakeningOS/VISTA-24M/evaluation/learning_curve.json
-
curl -L -o learning_curve.json https://huggingface.co/AwakeningOS/VISTA-24M/resolve/main/evaluation/learning_curve.json
2.79 kB
| [ | |
| { | |
| "words_m": 10, | |
| "blimp_filtered": 65.33, | |
| "supplement_filtered": 57.34, | |
| "ewok_filtered": 49.8, | |
| "entity_tracking": 17.78, | |
| "comps": 49.82, | |
| "global_piqa_parallel": 23.3, | |
| "global_piqa_nonparallel": 43.0, | |
| "six_task_mean": 45.53666666666666 | |
| }, | |
| { | |
| "words_m": 20, | |
| "blimp_filtered": 67.45, | |
| "supplement_filtered": 56.46, | |
| "ewok_filtered": 49.97, | |
| "entity_tracking": 18.26, | |
| "comps": 51.01, | |
| "global_piqa_parallel": 20.39, | |
| "global_piqa_nonparallel": 48.0, | |
| "six_task_mean": 46.22416666666667 | |
| }, | |
| { | |
| "words_m": 30, | |
| "blimp_filtered": 67.11, | |
| "supplement_filtered": 57.17, | |
| "ewok_filtered": 50.61, | |
| "entity_tracking": 18.57, | |
| "comps": 51.41, | |
| "global_piqa_parallel": 23.3, | |
| "global_piqa_nonparallel": 46.0, | |
| "six_task_mean": 46.586666666666666 | |
| }, | |
| { | |
| "words_m": 40, | |
| "blimp_filtered": 68.0, | |
| "supplement_filtered": 56.46, | |
| "ewok_filtered": 51.19, | |
| "entity_tracking": 17.98, | |
| "comps": 51.41, | |
| "global_piqa_parallel": 22.33, | |
| "global_piqa_nonparallel": 48.0, | |
| "six_task_mean": 46.70083333333333 | |
| }, | |
| { | |
| "words_m": 50, | |
| "blimp_filtered": 68.62, | |
| "supplement_filtered": 55.74, | |
| "ewok_filtered": 51.17, | |
| "entity_tracking": 18.58, | |
| "comps": 51.52, | |
| "global_piqa_parallel": 26.21, | |
| "global_piqa_nonparallel": 46.0, | |
| "six_task_mean": 46.95583333333334 | |
| }, | |
| { | |
| "words_m": 60, | |
| "blimp_filtered": 67.84, | |
| "supplement_filtered": 55.73, | |
| "ewok_filtered": 51.71, | |
| "entity_tracking": 18.56, | |
| "comps": 51.86, | |
| "global_piqa_parallel": 22.33, | |
| "global_piqa_nonparallel": 45.0, | |
| "six_task_mean": 46.560833333333335 | |
| }, | |
| { | |
| "words_m": 70, | |
| "blimp_filtered": 67.67, | |
| "supplement_filtered": 55.8, | |
| "ewok_filtered": 51.83, | |
| "entity_tracking": 17.97, | |
| "comps": 51.48, | |
| "global_piqa_parallel": 27.18, | |
| "global_piqa_nonparallel": 46.0, | |
| "six_task_mean": 46.89000000000001 | |
| }, | |
| { | |
| "words_m": 80, | |
| "blimp_filtered": 67.73, | |
| "supplement_filtered": 58.41, | |
| "ewok_filtered": 52.83, | |
| "entity_tracking": 18.56, | |
| "comps": 51.32, | |
| "global_piqa_parallel": 28.16, | |
| "global_piqa_nonparallel": 51.0, | |
| "six_task_mean": 48.071666666666665 | |
| }, | |
| { | |
| "words_m": 90, | |
| "blimp_filtered": 67.34, | |
| "supplement_filtered": 55.9, | |
| "ewok_filtered": 51.99, | |
| "entity_tracking": 18.16, | |
| "comps": 51.45, | |
| "global_piqa_parallel": 23.3, | |
| "global_piqa_nonparallel": 47.0, | |
| "six_task_mean": 46.665 | |
| }, | |
| { | |
| "words_m": 100, | |
| "blimp_filtered": 67.41, | |
| "supplement_filtered": 56.27, | |
| "ewok_filtered": 51.89, | |
| "entity_tracking": 18.26, | |
| "comps": 51.25, | |
| "global_piqa_parallel": 24.27, | |
| "global_piqa_nonparallel": 46.0, | |
| "six_task_mean": 46.70250000000001 | |
| } | |
| ] | |