Instructions to use SangBinCho/long_context_32k_testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SangBinCho/long_context_32k_testing with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/mnt/local_storage/.cache/huggingface/hub/models--meta-llama--Llama-2-13b-chat-hf/snapshots/ee41e514ee23be967cc6a698dba34c5fd08ab9b5") model = PeftModel.from_pretrained(base_model, "SangBinCho/long_context_32k_testing") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from SangBinCho/long_context_32k_testing: direct link, hf CLI and curl.
- Browser
- Download file 615 Bytes
-
https://huggingface.co/SangBinCho/long_context_32k_testing/resolve/main/adapter_config.json
- Command line
-
hf download hf://SangBinCho/long_context_32k_testing/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/SangBinCho/long_context_32k_testing/resolve/main/adapter_config.json
615 Bytes
| {"auto_mapping": null, "base_model_name_or_path": "/mnt/local_storage/.cache/huggingface/hub/models--meta-llama--Llama-2-13b-chat-hf/snapshots/ee41e514ee23be967cc6a698dba34c5fd08ab9b5", "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": [], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "embed_tokens", "lm_head"], "task_type": "CAUSAL_LM", "context_length": 32768} |