Instructions to use Trelis/Llama-2-13b-chat-hf-stanford-nil-policy-ft-adapters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Trelis/Llama-2-13b-chat-hf-stanford-nil-policy-ft-adapters with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-13b-chat-hf") model = PeftModel.from_pretrained(base_model, "Trelis/Llama-2-13b-chat-hf-stanford-nil-policy-ft-adapters") - Notebooks
- Google Colab
- Kaggle
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.1, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 8, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "self_attn.o_proj", | |
| "post_attention_layernorm.weight", | |
| "mlp.down_proj", | |
| "self_attn.rotary_emb.inv_freq", | |
| "self_attn.v_proj", | |
| "mlp.up_proj", | |
| "mlp.gate_proj", | |
| "lm_head.weight", | |
| "input_layernorm.weight", | |
| "self_attn.q_proj", | |
| "self_attn.k_proj", | |
| "model.norm.weight" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |