Instructions to use KETI-NLP/KoEVD-response-strategy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use KETI-NLP/KoEVD-response-strategy with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "KETI-NLP/KoEVD-response-strategy") - Notebooks
- Google Colab
- Kaggle
Download manifest.json from KETI-NLP/KoEVD-response-strategy: direct link, hf CLI and curl.
- Browser
- Download file 2.87 kB
-
https://huggingface.co/KETI-NLP/KoEVD-response-strategy/resolve/main/manifest.json
- Command line
-
hf download hf://KETI-NLP/KoEVD-response-strategy/manifest.json
-
curl -L -o manifest.json https://huggingface.co/KETI-NLP/KoEVD-response-strategy/resolve/main/manifest.json
2.87 kB
| { | |
| "format": "sha256-file-manifest-v1", | |
| "release_version": "0.1.0", | |
| "excludes": [ | |
| "manifest.json", | |
| ".git", | |
| "build/cache artifacts" | |
| ], | |
| "files": [ | |
| { | |
| "path": ".gitattributes", | |
| "bytes": 208, | |
| "sha256": "c9b0e1b95f6a860e137b3ecf07b98ccc5a11b0f44da9133a1cd3a0b2b173d397" | |
| }, | |
| { | |
| "path": "LICENSE.md", | |
| "bytes": 2907, | |
| "sha256": "3bd19513596e3e8d6b2ffb4356f9d2c46cf62dedf7f09b54ca72ad73a7fb8a2e" | |
| }, | |
| { | |
| "path": "PROVENANCE.json", | |
| "bytes": 540, | |
| "sha256": "b1834a5cddc0c6122710dfdbf04b03f0042d5e3870ce98b4b59dc12d272d7d6a" | |
| }, | |
| { | |
| "path": "README.md", | |
| "bytes": 9555, | |
| "sha256": "b0ef79a9e60705f27cfa1f847ecc5825fcbfff07d470a0b8fe09a9396cef5742" | |
| }, | |
| { | |
| "path": "adapter_config.json", | |
| "bytes": 1092, | |
| "sha256": "8d6f7a372f6d725977c3835a590a050cb4f1c5d62e3ad039a1c72fcebbc443ea" | |
| }, | |
| { | |
| "path": "adapter_model.safetensors", | |
| "bytes": 174655536, | |
| "sha256": "9d8f98865f96c50f8b247dfaa9716e1c2a39b012f8cfffd7937000b8a21edb98" | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "bytes": 4168, | |
| "sha256": "a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8" | |
| }, | |
| { | |
| "path": "metrics/response_strategy_full_corpus_metrics.json", | |
| "bytes": 5729, | |
| "sha256": "b055dfc6cd0060db4e1dd83dbcf3f1b1743d2b299e96ec096356d56bb9b61f39" | |
| }, | |
| { | |
| "path": "metrics/response_strategy_source_disjoint_validation_metrics.json", | |
| "bytes": 923, | |
| "sha256": "048b45c2812bcb55becbaa3acdd82f2cfc36e79484e26a613f4fde019de7f657" | |
| }, | |
| { | |
| "path": "review_fp16/adapter_config.json", | |
| "bytes": 1092, | |
| "sha256": "8d6f7a372f6d725977c3835a590a050cb4f1c5d62e3ad039a1c72fcebbc443ea" | |
| }, | |
| { | |
| "path": "review_fp16/adapter_model.safetensors", | |
| "bytes": 87361176, | |
| "sha256": "d79aeebbbc197335505397102bc099d9e7eb71d0afa97ef5aecb168d3f0f22be" | |
| }, | |
| { | |
| "path": "review_fp16/chat_template.jinja", | |
| "bytes": 4168, | |
| "sha256": "a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8" | |
| }, | |
| { | |
| "path": "review_fp16/tokenizer.json", | |
| "bytes": 11422650, | |
| "sha256": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506" | |
| }, | |
| { | |
| "path": "review_fp16/tokenizer_config.json", | |
| "bytes": 665, | |
| "sha256": "47bfa3e7727312946b29ac10d6dd0672d63cf7815b2a160b9523872040d2e536" | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "bytes": 11422650, | |
| "sha256": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506" | |
| }, | |
| { | |
| "path": "tokenizer_config.json", | |
| "bytes": 665, | |
| "sha256": "47bfa3e7727312946b29ac10d6dd0672d63cf7815b2a160b9523872040d2e536" | |
| } | |
| ], | |
| "documentation_update": "2026-09-15 camera-ready clarification; canonical data and model weights unchanged" | |
| } | |