Instructions to use k1h0/codellama-7b-ptuning-java with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use k1h0/codellama-7b-ptuning-java with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf") model = PeftModel.from_pretrained(base_model, "k1h0/codellama-7b-ptuning-java") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-371/adapter_config.json from k1h0/codellama-7b-ptuning-java: direct link, hf CLI and curl.
- Browser
- Download file 445 Bytes
-
https://huggingface.co/k1h0/codellama-7b-ptuning-java/resolve/main/checkpoint-371/adapter_config.json
- Command line
-
hf download hf://k1h0/codellama-7b-ptuning-java/checkpoint-371/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/k1h0/codellama-7b-ptuning-java/resolve/main/checkpoint-371/adapter_config.json
445 Bytes
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "codellama/CodeLlama-7b-hf", | |
| "encoder_dropout": 0.0, | |
| "encoder_hidden_size": 128, | |
| "encoder_num_layers": 2, | |
| "encoder_reparameterization_type": "MLP", | |
| "inference_mode": true, | |
| "num_attention_heads": 32, | |
| "num_layers": 32, | |
| "num_transformer_submodules": 1, | |
| "num_virtual_tokens": 20, | |
| "peft_type": "P_TUNING", | |
| "revision": null, | |
| "task_type": "CAUSAL_LM", | |
| "token_dim": 4096 | |
| } |