Skip to content

Commit 39c9547

Browse files
xyoniumxyonium
authored
Update index.yaml and add Qwen3.5 model files (#9237)
* Update index.yaml Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> * Add mmproj files for Qwen3.5 models Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> * Update file paths for Qwen models in index.yaml Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> * Update index.yaml Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> * Refactor Qwen3-Reranker-0.6B entry in index.yaml Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> * Update qwen3.yaml configuration parameters Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com> --------- Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>
1 parent 9b7d551 commit 39c9547

2 files changed

Lines changed: 86 additions & 3 deletions

File tree

‎gallery/index.yaml‎

Lines changed: 82 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1288,6 +1288,59 @@
12881288
- filename: llama-cpp/mmproj/Qwen3-VL-Reranker-8B.mmproj-f16.gguf
12891289
sha256: 15cd9bd4882dae771344f0ac204fce07de91b47c1438ada3861dfc817403c31e
12901290
uri: https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF/resolve/main/Qwen3-VL-Reranker-8B.mmproj-f16.gguf
1291+
- name: "qwen3-vl-reranker-2b-i1"
1292+
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
1293+
urls:
1294+
- https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-i1-GGUF
1295+
description: |
1296+
**Model Name:** Qwen3-VL-Reranker-2B-i1
1297+
**Base Model:** Qwen/Qwen3-VL-Reranker-2B
1298+
1299+
**Description:**
1300+
A high-performance multimodal reranking model for state-of-the-art cross-modal search. It supports 30+ languages and handles text, images, screenshots, videos, and mixed modalities. With 8B parameters and a 32K context length, it refines retrieval results by combining embedding vectors with precise relevance scores. Optimized for efficiency, it supports quantized versions (e.g., Q8_0, Q4_K_M) and is ideal for applications requiring accurate multimodal content matching.
1301+
1302+
**Key Features:**
1303+
- **Multimodal**: Text, images, videos, and mixed content.
1304+
- **Language Support**: 30+ languages.
1305+
- **Quantization**: Available in Q8_0 (best quality), Q4_K_M (fast, recommended), and lower-precision options.
1306+
- **Performance**: Outperforms base models in retrieval tasks (e.g., JinaVDR, ViDoRe v3).
1307+
- **Use Case**: Enhances search pipelines by refining embeddings with precise relevance scores.
1308+
1309+
**Downloads:**
1310+
- [GGUF Files](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-i1-GGUF) (e.g., `Qwen3-VL-Reranker-2B.i1-Q4_K_M.gguf`).
1311+
1312+
**Usage:**
1313+
- Requires `transformers`, `qwen-vl-utils`, and `torch`.
1314+
- Example: `from scripts.qwen3_vl_reranker import Qwen3VLReranker; model = Qwen3VLReranker(...)`
1315+
1316+
**Citation:**
1317+
@article{qwen3vlembedding, ...}
1318+
1319+
This description emphasizes its capabilities, efficiency, and versatility for multimodal search tasks.
1320+
overrides:
1321+
reranking: true
1322+
parameters:
1323+
model: llama-cpp/models/Qwen3-VL-Reranker-2B.i1-Q4_K_M.gguf
1324+
name: Qwen3-VL-Reranker-2B-i1-GGUF
1325+
backend: llama-cpp
1326+
template:
1327+
use_tokenizer_template: true
1328+
known_usecases:
1329+
- chat
1330+
function:
1331+
grammar:
1332+
disable: true
1333+
mmproj: llama-cpp/mmproj/Qwen3-VL-Reranker-2B.mmproj-f16.gguf
1334+
description: Imported from https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/
1335+
options:
1336+
- use_jinja:true
1337+
files:
1338+
- filename: llama-cpp/models/Qwen3-VL-Reranker-2B.i1-Q4_K_M.gguf
1339+
sha256: f19dfbceeef9f6ee1f7d0ff536d66e9b1b90424a4b8aa1d1777db43d20afdbc5
1340+
uri: https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-i1-GGUF/resolve/main/Qwen3-VL-Reranker-2B.i1-Q4_K_M.gguf
1341+
- filename: llama-cpp/mmproj/Qwen3-VL-Reranker-8B.mmproj-f16.gguf
1342+
sha256: d38b7ae347fc3e51726bfb9cba1b04885f1f005a4087d8070933e46509db5a6e
1343+
uri: https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.mmproj-f16.gguf
12911344
- name: "liquidai.lfm2-2.6b-transcript"
12921345
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
12931346
urls:
@@ -3095,6 +3148,35 @@
30953148
- filename: Qwen_Qwen3-30B-A3B-Q4_K_M.gguf
30963149
sha256: a015794bfb1d69cb03dbb86b185fb2b9b339f757df5f8f9dd9ebdab8f6ed5d32
30973150
uri: huggingface://bartowski/Qwen_Qwen3-30B-A3B-GGUF/Qwen_Qwen3-30B-A3B-Q4_K_M.gguf
3151+
- !!merge <<: *qwen3
3152+
name: "qwen3-reranker-0.6b"
3153+
tags:
3154+
- qwen3
3155+
- reranker
3156+
- gguf
3157+
- gpu
3158+
- cpu
3159+
urls:
3160+
- https://huggingface.co/Qwen/Qwen3-Reranker-0.6B
3161+
description: |
3162+
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
3163+
**Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58), while the reranking model excels in various text retrieval scenarios.
3164+
**Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.
3165+
**Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.
3166+
**Qwen3-Reranker-0.6B** has the following features:
3167+
- Model Type: Text Reranking
3168+
- Supported Languages: 100+ Languages
3169+
- Number of Paramaters: 0.6B
3170+
- Context Length: 32k
3171+
- Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0, f16
3172+
overrides:
3173+
reranking: true
3174+
parameters:
3175+
model: Qwen3-Reranker-0.6B.Q8_0.gguf
3176+
files:
3177+
- filename: Qwen3-Reranker-0.6B.Q8_0.gguf
3178+
uri: huggingface://mradermacher/Qwen3-Reranker-0.6B-GGUF/Qwen3-Reranker-0.6B.Q8_0.gguf
3179+
sha256: c525a7449243f690a7062e6377d6cf5adbb289354bd4316312367cd20e187ab7
30983180
- !!merge <<: *qwen3
30993181
name: "qwen3-235b-a22b-instruct-2507"
31003182
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png

‎gallery/qwen3.yaml‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,10 @@
22
name: "qwen3"
33

44
config_file: |
5-
mmap: true
5+
parameters:
6+
context_size: 8192
7+
f16: true
8+
mmap: true
69
backend: "llama-cpp"
710
template:
811
chat_message: |
@@ -36,8 +39,6 @@ config_file: |
3639
<|im_start|>assistant
3740
completion: |
3841
{{.Input}}
39-
context_size: 8192
40-
f16: true
4142
stopwords:
4243
- '<|im_end|>'
4344
- '<dummy32000>'

0 commit comments

Comments
 (0)