Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Instructions to use hypaai/hypa-tiny-keys-old with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hypaai/hypa-tiny-keys-old with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hypaai/hypa-tiny-keys-old") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hypaai/hypa-tiny-keys-old") model = AutoModelForCausalLM.from_pretrained("hypaai/hypa-tiny-keys-old", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hypaai/hypa-tiny-keys-old with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hypaai/hypa-tiny-keys-old" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hypaai/hypa-tiny-keys-old", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hypaai/hypa-tiny-keys-old
- SGLang
How to use hypaai/hypa-tiny-keys-old 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 "hypaai/hypa-tiny-keys-old" \ --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": "hypaai/hypa-tiny-keys-old", "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 "hypaai/hypa-tiny-keys-old" \ --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": "hypaai/hypa-tiny-keys-old", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use hypaai/hypa-tiny-keys-old with Docker Model Runner:
docker model run hf.co/hypaai/hypa-tiny-keys-old
Commit History
-
Training in progress, step 40584
Verified signature9a30c3d -
Training in progress, step 33820
Verified signaturec5b9407 -
Training in progress, step 27056
Verified signatureb6a48c7 -
Training in progress, step 20292
Verified signaturea3639de -
Training in progress, step 13528
Verified signature708aaf5 -
Training in progress, step 6764
Verified signatureee20412
-
Model save
Verified signature841f667 -
Training in progress, step 60000
Verified signaturea8caac9 -
Training in progress, step 59500
Verified signature3e42a13 -
Training in progress, step 59000
Verified signature6a43076 -
Training in progress, step 58500
Verified signature26d3e02 -
Training in progress, step 58000
Verified signature382d2e1 -
Training in progress, step 57500
Verified signature484bedf -
Training in progress, step 57000
Verified signature6957ad3 -
Training in progress, step 56500
Verified signaturedb7285a -
Training in progress, step 56000
Verified signatureed8fe5f -
Training in progress, step 55500
Verified signatureee3c077 -
Training in progress, step 55000
Verified signature15dee0e -
Training in progress, step 54500
Verified signatureea7a458 -
Training in progress, step 54000
Verified signature277b38b -
Training in progress, step 53500
Verified signature64624ee -
Training in progress, step 53000
Verified signature901da64 -
Training in progress, step 52500
Verified signature195b20e -
Training in progress, step 52000
Verified signaturea21f232 -
Training in progress, step 51500
Verified signature4333392 -
Training in progress, step 51000
Verified signature9677c0c -
Training in progress, step 50500
Verified signature8fcfe28 -
Training in progress, step 50000
Verified signature1ec4e23 -
Training in progress, step 49500
Verified signature7fea704 -
Training in progress, step 49000
Verified signature5f05699 -
Training in progress, step 48500
Verified signatureda5adda -
Training in progress, step 48000
Verified signature96981c2 -
Training in progress, step 47500
Verified signature21ce1e4 -
Training in progress, step 47000
Verified signature111b516 -
Training in progress, step 46500
Verified signature39b9bbe -
Training in progress, step 46000
Verified signature08a11c6 -
Training in progress, step 45500
Verified signature0b503d4 -
Training in progress, step 45000
Verified signature90ff3af -
Training in progress, step 44500
Verified signature282e531 -
Training in progress, step 44000
Verified signature0a4287a -
Training in progress, step 43500
Verified signature0828811 -
Training in progress, step 43000
Verified signaturec166fc2 -
Training in progress, step 42500
Verified signature3122fa2 -
Training in progress, step 42000
Verified signature88ece3e -
Training in progress, step 41500
Verified signatureaae1c76 -
Training in progress, step 41000
Verified signaturef9d7b76 -
Training in progress, step 40500
Verified signaturecc75aae -
Training in progress, step 40000
Verified signature7335701 -
Training in progress, step 39500
Verified signature26d41bd -
Training in progress, step 39000
Verified signaturec543f46