mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-22 13:22:03 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore(model gallery): 🤖 add 1 new models via gallery agent (#6784)

Browse Source 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
LocalAI [bot]
2025-10-26 21:22:58 +01:00
committed by GitHub
parent ce2f8828f9
commit 0c0186d866
1 changed files with 21 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
gallery/index.yaml
View File

@@ -22657,3 +22657,24 @@
- filename: gpt-oss-20b-claude-4-distill.i1-Q4_K_M.gguf
sha256: 333bdbde0a933b62f2050f384879bfaea7db7a5fbb26ee151fbbdc3c95f510dd
uri: huggingface://mradermacher/gpt-oss-20b-claude-4-distill-i1-GGUF/gpt-oss-20b-claude-4-distill.i1-Q4_K_M.gguf
- !!merge <<: *llama3
name: "70b_book_stock-i1"
urls:
- https://huggingface.co/mradermacher/70B_Book_stock-i1-GGUF
description: |
**Model Name:** Book_stock
**Base Model:** huihui-ai/Llama-3.3-70B-Instruct-abliterated
**Type:** Fine-tuned, merged LLM (70B parameters)
**Framework:** Transformers (Hugging Face)
**Merge Method:** Model Stock (via MergeKit)
**Description:**
A high-performance, 70-billion-parameter language model fine-tuned and merged using the *Model Stock* technique. Built upon the **Llama-3.3-70B-Instruct-abliterated** base, this model integrates multiple specialized LoRA adapters (Book_RPv05, Book_RPv1, Book_RPv15, Book_RPvfinal) to enhance instruction-following, reasoning, and domain-specific knowledge—particularly in book-related content, narrative reasoning, and creative writing.
Optimized for strong performance in dialogue and creative tasks, with support for Llama 3-style chat templates and BFloat16 precision. Ideal for applications requiring deep reasoning, long-form generation, and nuanced instruction handling.
**Use Case:** Creative writing, content generation, dialogue systems, educational tools, and advanced reasoning tasks.
**Note:** This model is not a direct release by the original authors but a community-driven merge; the original base model is available at [huihui-ai/Llama-3.3-70B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated).
overrides:
parameters:
model: mradermacher/70B_Book_stock-i1-GGUF