Text Generation
Transformers
Safetensors
English
lowonmind
tiny-lm
pretrained-from-scratch
scaling-limits
custom_code
Instructions to use DedeProGames/LowOnMind-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DedeProGames/LowOnMind-1M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DedeProGames/LowOnMind-1M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DedeProGames/LowOnMind-1M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DedeProGames/LowOnMind-1M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DedeProGames/LowOnMind-1M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DedeProGames/LowOnMind-1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DedeProGames/LowOnMind-1M
- SGLang
How to use DedeProGames/LowOnMind-1M 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 "DedeProGames/LowOnMind-1M" \ --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": "DedeProGames/LowOnMind-1M", "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 "DedeProGames/LowOnMind-1M" \ --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": "DedeProGames/LowOnMind-1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DedeProGames/LowOnMind-1M with Docker Model Runner:
docker model run hf.co/DedeProGames/LowOnMind-1M
| { | |
| "data": "fineweb_edu_200M_v1024.uint16.bin", | |
| "base": "LowOnMind-1M", | |
| "derived_from": "DedeProGames/LowOnMind-300k", | |
| "dataset": "HuggingFaceFW/fineweb-edu:sample-10BT", | |
| "tokenizer": "byte-level BPE 1024", | |
| "params": 985152, | |
| "seq_len": 512, | |
| "batch_size": 64, | |
| "grad_accum": 1, | |
| "max_steps": 6103, | |
| "total_tokens": 199983104, | |
| "lr": 0.0015, | |
| "min_lr": 0.00015, | |
| "warmup_steps": 250, | |
| "weight_decay": 0.1, | |
| "grad_clip": 1.0, | |
| "val_tokens": 2000000, | |
| "eval_every": 500, | |
| "eval_batches": 40, | |
| "device": "cuda", | |
| "dtype": "float16", | |
| "compile": true, | |
| "seed": 1337, | |
| "train_minutes": 10.6, | |
| "final_val_loss": 2.9908, | |
| "final_val_ppl": 19.901, | |
| "bits_per_char": 1.8361, | |
| "chars_per_token": 2.35, | |
| "reused_tokenizer_from": "DedeProGames/LowOnMind-300k", | |
| "baseline": { | |
| "name": "LowOnMind-300k", | |
| "params": 296960, | |
| "val_loss": 3.2982, | |
| "val_ppl": 27.06, | |
| "bpc": 2.03, | |
| "bench_elo": 833, | |
| "bench_acc": 0.266 | |
| }, | |
| "lexicon": { | |
| "model_real_word_rate": 0.9798, | |
| "corpus_real_word_rate": 0.9839, | |
| "words_scored": 5647, | |
| "samples": 64, | |
| "top_nonwords": [ | |
| [ | |
| "sculieness", | |
| 1 | |
| ], | |
| [ | |
| "lockholm", | |
| 1 | |
| ], | |
| [ | |
| "scul", | |
| 1 | |
| ], | |
| [ | |
| "purpled", | |
| 1 | |
| ], | |
| [ | |
| "paradigmar", | |
| 1 | |
| ], | |
| [ | |
| "prefection", | |
| 1 | |
| ], | |
| [ | |
| "frushing", | |
| 1 | |
| ], | |
| [ | |
| "fullly", | |
| 1 | |
| ], | |
| [ | |
| "laxation", | |
| 1 | |
| ], | |
| [ | |
| "gulliel", | |
| 1 | |
| ], | |
| [ | |
| "annal", | |
| 1 | |
| ], | |
| [ | |
| "backg", | |
| 1 | |
| ], | |
| [ | |
| "warehorship", | |
| 1 | |
| ], | |
| [ | |
| "bulken", | |
| 1 | |
| ], | |
| [ | |
| "colle", | |
| 1 | |
| ] | |
| ] | |
| }, | |
| "samples": [ | |
| { | |
| "prompt": "The ", | |
| "text": "The veil-group, where is used to solve solar passwords and vegetables. It is often very important to reduce their treatments, including checkouts, labs, maintenance, mental groups, chemicals and maintenance costs. These literally confirmed elements are the most commonly used in the elementary front, solar energy, a" | |
| }, | |
| { | |
| "prompt": "Photosynthesis is ", | |
| "text": "Photosynthesis is essential to prevent disease infection. These types of disease include:\n\u2022 Transformation of Brook Scientific World Organization\n\u2022 Effectiveness of a diagnosis is commonly diagnosed with diagnosis. The Cultural Disorder is an important factor in diagnosis. Analysis of this purpose can be considered." | |
| }, | |
| { | |
| "prompt": "In 1969, ", | |
| "text": "In 1969, 8, 1999, Michael Kerzin, Anderson, 1997, Scotland, 1993, 1,359, p. 547\u2013414\nOur war was chosen in the West of Europe, Papua Party, Ottoman Economy, Pluto Mountains, and Evans, 1854, 1946, Maine, 1888-81, p" | |
| }, | |
| { | |
| "prompt": "Students should ", | |
| "text": "Students should identify their learners and adults.\nThe United States has free quotations in the world that can help them with this curriculum and finding problem concerning these funding.\nOne major solutions for malnutrition in South East and Africa is a way to limit half its own loop. This is the best way to ensure that the drills of the state and" | |
| } | |
| ], | |
| "history": [ | |
| { | |
| "step": 500, | |
| "val_loss": 3.6402, | |
| "val_ppl": 38.099 | |
| }, | |
| { | |
| "step": 1000, | |
| "val_loss": 3.3854, | |
| "val_ppl": 29.528 | |
| }, | |
| { | |
| "step": 1500, | |
| "val_loss": 3.2837, | |
| "val_ppl": 26.673 | |
| }, | |
| { | |
| "step": 2000, | |
| "val_loss": 3.2305, | |
| "val_ppl": 25.292 | |
| }, | |
| { | |
| "step": 2500, | |
| "val_loss": 3.187, | |
| "val_ppl": 24.216 | |
| }, | |
| { | |
| "step": 3000, | |
| "val_loss": 3.1488, | |
| "val_ppl": 23.308 | |
| }, | |
| { | |
| "step": 3500, | |
| "val_loss": 3.118, | |
| "val_ppl": 22.602 | |
| }, | |
| { | |
| "step": 4000, | |
| "val_loss": 3.0804, | |
| "val_ppl": 21.766 | |
| }, | |
| { | |
| "step": 4500, | |
| "val_loss": 3.0496, | |
| "val_ppl": 21.107 | |
| }, | |
| { | |
| "step": 5000, | |
| "val_loss": 3.0375, | |
| "val_ppl": 20.853 | |
| }, | |
| { | |
| "step": 5500, | |
| "val_loss": 3.0119, | |
| "val_ppl": 20.326 | |
| }, | |
| { | |
| "step": 6000, | |
| "val_loss": 3.0165, | |
| "val_ppl": 20.42 | |
| }, | |
| { | |
| "step": 6103, | |
| "val_loss": 3.0055, | |
| "val_ppl": 20.195 | |
| } | |
| ] | |
| } |