# Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B

Model from Hugging Face for text generation: Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B
- Hosting: hosted (11 files)
- Files: 11 hosted of 17 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 11 files, 16.1 GB
- Full repo upstream: 57.9 GB
- Recommended file: 4.92 GB (Q4_K_M) · ggml-model-q4_k_m.gguf
- Parameters: 8B
- Download: https://huggingbay.xyz/artifact/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/download-plan)
- Per-file SHA-256: available for 11 of 11 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 127
- Stars: 3
- Card completeness: 96%

## Description

External Hugging Face catalog record for Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-rlhf-dpo-8B. Task: text generation. Library: transformers. Languages: ko, en, jp, cn. Datasets referenced by card metadata: Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset, Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset, Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface. Base model: NousResearch/Meta-Llama-3.1-8B-Instruct. Popularity signal at import: 181 downloads and 3 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Base model: NousResearch/Meta-Llama-3.1-8B-Instruct
- Task categories: text-generation
- Languages: ko, en, jp, cn
- Referenced datasets: Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset, Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset, Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled
- File hints: 16 upstream file samples

## Referenced Data

- Dataset: Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset
- Dataset: Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset
- Dataset: Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface
- Dataset: Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface
- Dataset: Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface
- Dataset: Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface
- Dataset: Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface
- Dataset: Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled
- Dataset: maywell/ko_Ultrafeedback_binarized

## File Hints

- .gitattributes (1.8 KB)
- README.md (2.2 KB)
- config.json (917 B)
- generation_config.json (184 B)
- ggml-model-bf16.gguf (15 GB) LFS
- ggml-model-q4_k_m.gguf (4.6 GB) LFS
- ggml-model-q5_k_m.gguf (5.3 GB) LFS
- ggml-model-q6_k.gguf (6.1 GB) LFS
- ggml-model-q8_0.gguf (8.0 GB) LFS
- model-00001-of-00004.safetensors (4.6 GB) LFS
- model-00002-of-00004.safetensors (4.7 GB) LFS
- model-00003-of-00004.safetensors (4.6 GB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-03T01:00:55.766Z.
- Open license detected as apache-2.0.
- Model card references dataset context: Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset, Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset, Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-saxo-linkbricks-horizon-ai-korean-llama3-1-sft-rlhf-dpo-8b/decentralized-fallbacks