mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-22 15:49:12 -04:00
chore(model gallery): 🤖 add 1 new models via gallery agent (#10439)
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]
@@ -1,4 +1,96 @@
|
||||
---
|
||||
- name: "glm-5.2"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/unsloth/GLM-5.2-GGUF
|
||||
description: |
|
||||
# GLM-5.2
|
||||
|
||||
👋 Join our WeChat or Discord community.
|
||||
|
||||
📖 Check out the GLM-5.2 blog and GLM-5 Technical report.
|
||||
|
||||
📍 Use GLM-5.2 API services on Z.ai API Platform.
|
||||
|
||||
🔜 Try GLM-5.2 here.
|
||||
|
||||
[Paper]
|
||||
[GitHub]
|
||||
|
||||
## Introduction
|
||||
|
||||
We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**. GLM-5.2's new capabilities include:
|
||||
- **Solid 1M Context:** A solid 1M-token context that stably sustains long-horizon work
|
||||
- **Advanced Coding with Flexible Effort**: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency
|
||||
- **Improved Architecture**: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20%
|
||||
- **Pure Open**: An MIT open-source license — no regional limits, technical access without borders
|
||||
|
||||
## Benchmark
|
||||
|
||||
## Serve GLM-5.2 Locally
|
||||
|
||||
...
|
||||
license: "mit"
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
icon: https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_52.png
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
options:
|
||||
- use_jinja:true
|
||||
- spec_type:draft-mtp
|
||||
- spec_n_max:6
|
||||
- spec_p_min:0.75
|
||||
parameters:
|
||||
min_p: 0.01
|
||||
model: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
|
||||
sha256: 3256ac8c290273f0965ff39e93a8bcd07dc99bcd23e923bd4b7306ef39061038
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00001-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00002-of-00011.gguf
|
||||
sha256: 1020105e78d862988a6cabb3a78eafa75f29666ab8a5fd10de1b9b8c8a6bc5e8
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00002-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00003-of-00011.gguf
|
||||
sha256: 0b36f406e120759290894ea4960d5086f9b362a8c8f9c7fcaad24b4471172efb
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00003-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00004-of-00011.gguf
|
||||
sha256: 04b19199f52ba29e7f9966b15df3fbc2d1e5c56cd6343c405076be7174d49d32
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00004-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00005-of-00011.gguf
|
||||
sha256: 5cb76d724ee16e80c1cb6aba29aacd76161e7a6f147079be3447501c06d95f2c
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00005-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00006-of-00011.gguf
|
||||
sha256: ec2c65255c834b686f066e350bc5b8d8a7020cd1133f0ee9e819d2fb5d3afad0
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00006-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00007-of-00011.gguf
|
||||
sha256: 53c8328852ca0b6791a9a9243bcc56157305adca8526a646054389845e7445a9
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00007-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00008-of-00011.gguf
|
||||
sha256: 9a23bfb21c5f6fcc94b0329c108ec1ef3fdbd815c57eeb0bf105d26861d7271e
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00008-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00009-of-00011.gguf
|
||||
sha256: 71088054fb1a09a4f38e2ee8a726526790660a4f77ead817f75cb7a484bdb0b8
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00009-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00010-of-00011.gguf
|
||||
sha256: 848db99658faf24971df23638281305a15bdc187cbcaed968952ed9e9c835b50
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00010-of-00011.gguf
|
||||
- filename: llama-cpp/models/GLM-5.2-GGUF/GLM-5.2-UD-Q4_K_M-00011-of-00011.gguf
|
||||
sha256: 629e23bce250fb500d9a190de7249c2882af524aacc112ce507a871ed5bebf90
|
||||
uri: https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/main/UD-Q4_K_M/GLM-5.2-UD-Q4_K_M-00011-of-00011.gguf
|
||||
- name: "qwen3.6-35b-a3b-nvfp4-mtp"
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
|
||||
Reference in New Issue
Block a user