Summarization
Transformers
Safetensors
English
phi
text-generation
arxiv
custom_code
text-generation-inference
Instructions to use AlgorithmicResearchGroup/phi-physics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlgorithmicResearchGroup/phi-physics with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="AlgorithmicResearchGroup/phi-physics", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AlgorithmicResearchGroup/phi-physics", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("AlgorithmicResearchGroup/phi-physics", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from AlgorithmicResearchGroup/phi-physics: direct link, hf CLI and curl.
- Browser
- Download file 507 Bytes
-
https://huggingface.co/AlgorithmicResearchGroup/phi-physics/resolve/main/adapter_config.json
- Command line
-
hf download hf://AlgorithmicResearchGroup/phi-physics/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/AlgorithmicResearchGroup/phi-physics/resolve/main/adapter_config.json
507 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "microsoft/phi-1_5", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "Wqkv", | |
| "fc2", | |
| "fc1", | |
| "out_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |