Text Generation
Transformers
Safetensors
qwen2
phai-ide
science
code
tool-use
sft
lora
conversational
text-generation-inference
Instructions to use AItonomy/PhAI-IDE-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AItonomy/PhAI-IDE-72B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AItonomy/PhAI-IDE-72B") 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("AItonomy/PhAI-IDE-72B") model = AutoModelForCausalLM.from_pretrained("AItonomy/PhAI-IDE-72B", 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 AItonomy/PhAI-IDE-72B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AItonomy/PhAI-IDE-72B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AItonomy/PhAI-IDE-72B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AItonomy/PhAI-IDE-72B
- SGLang
How to use AItonomy/PhAI-IDE-72B 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 "AItonomy/PhAI-IDE-72B" \ --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": "AItonomy/PhAI-IDE-72B", "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 "AItonomy/PhAI-IDE-72B" \ --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": "AItonomy/PhAI-IDE-72B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AItonomy/PhAI-IDE-72B with Docker Model Runner:
docker model run hf.co/AItonomy/PhAI-IDE-72B
Commit History
29 days ago
-
Resolve README conflict with main; preserve unified model card
da68ab0 -
Simplify published comparisons to complete benchmark configurations
Verified signatureUse six compact benchmark rows with twelve similarly sized published-model references. Remove item-count annotations and retain comparisons backed by complete benchmark configurations. Preserve the ScienceAccelBench section unchanged.47b4732 -
Compact published-model comparisons; preserve science results table
Verified signatureGroup 27 previously sourced comparisons with similarly sized published models into 10 benchmark rows. Include reference links, parameter counts, score differences, and evaluation-scope notes. Restore the original ScienceAccelBench table and section unchanged.7ab5849 -
Add benchmark gains in compact model-level tables
Verified signatureRestore 14 previously verified public-benchmark improvements in three model rows grouped by reasoning, knowledge, and code. Compact the ScienceAccelBench environment table to two model rows. Preserve paired scores, gains, and subset labels.0d56bc1 -
Unify README for the PhAI-IDE model family
Verified signaturePresent PhAI-IDE-4B, PhAI-IDE-9B, and PhAI-IDE-72B together with a shared model table, verified ScienceAccelBench results, training description, and concise quick start. Retain repository-specific base-model and license metadata.53d2a7e -
Expand same-scale benchmark comparisons (#2)
- Expand same-scale benchmark comparisons (e06b9635176389168e1fc39517aae648eca5305e)79fdcb6 -
Update README with verified ScienceAccelBench results
Verified signatureUpdate this model card with verified ScienceAccelBench results. Remove public-benchmark comparison tables and keep results specific to this model size. Training data is sourced from AItonomy/ScienceIDE.e646fba -
Update PhAI-IDE-72B model card (#1)
- Update PhAI-IDE-72B model card (ce5751d818fc4755a24c0e55a9c2ed9632bb144e)8dc9f4a -
Add PhAI-IDE-72B model card
Verified signature2e6eec3
30 days ago
-
Add PhAI-IDE-72B configuration and tokenizer assets
Verified signature22a07ea -
Add 72B index after verifying all 37 weight shards
Verified signature217261d -
Add JEPA-Anything-72B model-00029-of-00037.safetensors
Verified signature509dcb3 -
Add JEPA-Anything-72B model-00024-of-00037.safetensors
Verified signature3018744 -
Add JEPA-Anything-72B model-00031-of-00037.safetensors
Verified signature8100a89 -
Add JEPA-Anything-72B model-00023-of-00037.safetensors
Verified signature3e47f1b -
Add JEPA-Anything-72B model-00023-of-00037.safetensors
Verified signature61449e3 -
Add JEPA-Anything-72B model-00025-of-00037.safetensors
Verified signaturedb704da -
Add JEPA-Anything-72B model-00030-of-00037.safetensors
Verified signature7f42198 -
Add JEPA-Anything-72B model-00032-of-00037.safetensors
Verified signaturec394a79 -
Add JEPA-Anything-72B model-00033-of-00037.safetensors
Verified signature55f77df -
Add verified preuploaded 72B shards 26 and 34
Verified signaturebb9c4f5 -
Add JEPA-Anything-72B model-00022-of-00037.safetensors
Verified signature1338a10 -
Add JEPA-Anything-72B model-00021-of-00037.safetensors
Verified signature138e8bd -
Add JEPA-Anything-72B model-00020-of-00037.safetensors
Verified signature3f514c9 -
Add JEPA-Anything-72B model-00019-of-00037.safetensors
Verified signature4f8917d -
Add JEPA-Anything-72B model-00018-of-00037.safetensors
Verified signature709b78a -
Add JEPA-Anything-72B model-00017-of-00037.safetensors
Verified signatureed01e5e -
Add JEPA-Anything-72B model-00027-of-00037.safetensors
Verified signature7d6a604 -
Add JEPA-Anything-72B model-00035-of-00037.safetensors
Verified signaturee34c5a5 -
Add JEPA-Anything-72B model-00016-of-00037.safetensors
Verified signature2679b2a -
Add JEPA-Anything-72B model-00037-of-00037.safetensors
Verified signaturee9aa76c -
Add JEPA-Anything-72B model-00028-of-00037.safetensors
Verified signature4bc2a49 -
Add JEPA-Anything-72B model-00015-of-00037.safetensors
Verified signatureac33b4a -
Add JEPA-Anything-72B model-00014-of-00037.safetensors
Verified signaturea727d2d -
Add JEPA-Anything-72B model-00013-of-00037.safetensors
Verified signature32b48ad -
Add JEPA-Anything-72B model-00012-of-00037.safetensors
Verified signature8ea3db8 -
Add JEPA-Anything-72B model-00011-of-00037.safetensors
Verified signature7735f18 -
Add JEPA-Anything-72B model-00010-of-00037.safetensors
Verified signature3de2b06 -
Add JEPA-Anything-72B model-00036-of-00037.safetensors
Verified signature254a0b2 -
Add JEPA-Anything-72B model-00009-of-00037.safetensors
Verified signature7db2316 -
Add JEPA-Anything-72B model-00008-of-00037.safetensors
Verified signature3c88002 -
Add JEPA-Anything-72B model-00007-of-00037.safetensors
Verified signature2f7e711 -
Add JEPA-Anything-72B model-00006-of-00037.safetensors
Verified signature9b60747 -
Add JEPA-Anything-72B model-00005-of-00037.safetensors
Verified signaturea59a963 -
Add JEPA-Anything-72B model-00004-of-00037.safetensors
Verified signature7583af1 -
Add JEPA-Anything-72B model-00003-of-00037.safetensors
Verified signatureb52a709 -
Add JEPA-Anything-72B model-00001-of-00037.safetensors
Verified signature7cc9033 -
Add JEPA-Anything-72B model-00002-of-00037.safetensors
Verified signature685ec37 -
initial commit
Verified signature13609f8