Image-Text-to-Text
GGUF
llama-cpp
quantized
clairic
qwen3_5
multimodal
structured-output
information-extraction
imatrix
conversational
Instructions to use Xylolabs/clairic-flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Xylolabs/clairic-flash-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Xylolabs/clairic-flash-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Xylolabs/clairic-flash-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Xylolabs/clairic-flash-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xylolabs/clairic-flash-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Xylolabs/clairic-flash-GGUF:Q4_K_M
- Ollama
How to use Xylolabs/clairic-flash-GGUF with Ollama:
ollama run hf.co/Xylolabs/clairic-flash-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use Xylolabs/clairic-flash-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Xylolabs/clairic-flash-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Xylolabs/clairic-flash-GGUF with Docker Model Runner:
docker model run hf.co/Xylolabs/clairic-flash-GGUF:Q4_K_M
- Lemonade
How to use Xylolabs/clairic-flash-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Xylolabs/clairic-flash-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.clairic-flash-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Xylolabs/clairic-flash-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default Xylolabs/clairic-flash-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Xylolabs/clairic-flash-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/clairic-flash-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "Xylolabs/clairic-flash-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Add model card, license, notice and chart
Browse files- .gitattributes +1 -0
- LICENSE +202 -0
- NOTICE +1 -0
- README.md +282 -0
- kl.png +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
clairic-flash-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
clairic-flash-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
kl.png filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright 2026 Alibaba Cloud
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
NOTICE
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Clairic Flash GGUF quantizations. Source model: Cloudflare/clairic-flash, Copyright 2026 Cloudflare, Inc., Apache License 2.0 (LICENSE, Cloudflare's text unchanged); it is a fine-tune of Qwen/Qwen3.5-9B, Copyright the Qwen Team, Alibaba Group, Apache License 2.0. Modified by Xylolabs: quantization and conversion to GGUF (see README.md). Not affiliated with or endorsed by Cloudflare or Alibaba.
|
README.md
ADDED
|
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
license_link: LICENSE
|
| 4 |
+
base_model:
|
| 5 |
+
- Cloudflare/clairic-flash
|
| 6 |
+
base_model_relation: quantized
|
| 7 |
+
library_name: gguf
|
| 8 |
+
pipeline_tag: image-text-to-text
|
| 9 |
+
tags:
|
| 10 |
+
- gguf
|
| 11 |
+
- llama-cpp
|
| 12 |
+
- quantized
|
| 13 |
+
- clairic
|
| 14 |
+
- qwen3_5
|
| 15 |
+
- multimodal
|
| 16 |
+
- structured-output
|
| 17 |
+
- information-extraction
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
<div align="center">
|
| 21 |
+
|
| 22 |
+
<img class="block dark:hidden mx-auto" src="https://raw.githubusercontent.com/XylolabsInc/tensix-bfp-gptq/main/assets/xylolabs-lockup.svg" alt="Xylolabs" width="256" height="40">
|
| 23 |
+
<img class="hidden dark:block mx-auto" src="https://raw.githubusercontent.com/XylolabsInc/tensix-bfp-gptq/main/assets/xylolabs-lockup-dark.svg" alt="Xylolabs" width="256" height="40">
|
| 24 |
+
|
| 25 |
+
<h1>Clairic Flash GGUF</h1>
|
| 26 |
+
|
| 27 |
+
[](https://huggingface.co/Cloudflare/clairic-flash)
|
| 28 |
+
[](#files)
|
| 29 |
+
[](https://huggingface.co/Xylolabs/clairic-flash-GGUF/blob/main/LICENSE)
|
| 30 |
+
[](https://github.com/ggml-org/llama.cpp)
|
| 31 |
+
|
| 32 |
+
</div>
|
| 33 |
+
|
| 34 |
+
GGUF quants of [Cloudflare/clairic-flash](https://huggingface.co/Cloudflare/clairic-flash) (9B, a fine-tune of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for structured extraction) for llama.cpp, on CUDA, Metal or CPU. Stock llama.cpp runs it, with image input through the mmproj file.
|
| 35 |
+
|
| 36 |
+
- **Files:** Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q4_K_S, IQ4_XS, Q3_K_M, IQ3_M and Q2_K (each one file with the tokenizer and chat template inside), the vision projector `mmproj-clairic-flash-BF16.gguf`, and the importance matrix.
|
| 37 |
+
- **Q4_K_M:** KL 0.0468 from the f32 reference, top-1 93.46 %.
|
| 38 |
+
- **Cloudflare's description:** [below](#cloudflares-original-model-description), unchanged.
|
| 39 |
+
|
| 40 |
+
## Files
|
| 41 |
+
|
| 42 |
+
- `clairic-flash-<QUANT>.gguf` is one file per quant: the language model.
|
| 43 |
+
- `mmproj-clairic-flash-BF16.gguf` is the vision encoder, for image input.
|
| 44 |
+
- `clairic-flash.imatrix.gguf` is the importance matrix.
|
| 45 |
+
|
| 46 |
+
| Quant | Size | PPL | Mean KL vs f32 reference | Same top-1 vs f32 reference |
|
| 47 |
+
|---|---|---|---|---|
|
| 48 |
+
| Q8_0 | 9.53 GB | 6.0278 | 0.0072 | 97.94% |
|
| 49 |
+
| Q6_K | 7.37 GB | 6.0361 | 0.0132 | 96.93% |
|
| 50 |
+
| Q5_K_M | 6.50 GB | 5.9699 | 0.0203 | 95.97% |
|
| 51 |
+
| Q4_K_M | 5.69 GB | 5.9742 | 0.0468 | 93.46% |
|
| 52 |
+
| Q4_K_S | 5.37 GB | 5.9592 | 0.0507 | 93.12% |
|
| 53 |
+
| IQ4_XS | 5.27 GB | 6.2223 | 0.0562 | 92.60% |
|
| 54 |
+
| Q3_K_M | 4.69 GB | 5.7594 | 0.1635 | 87.62% |
|
| 55 |
+
| IQ3_M | 4.48 GB | 6.7828 | 0.1510 | 87.25% |
|
| 56 |
+
| Q2_K | 3.93 GB | 5.3667 | 0.3112 | 82.21% |
|
| 57 |
+
|
| 58 |
+
How we measured:
|
| 59 |
+
|
| 60 |
+
- **Reference:** the model in transformers with f32 compute on Cloudflare's BF16 weights (PPL 6.0590).
|
| 61 |
+
- **KL, top-1, PPL:** 12 chunks of 4,096 tokens, scoring positions 2,048 to 4,095 of each (24,564 tokens): 9 held-out chat-formatted chunks (English, Korean, code, math, JSON extraction from a schema, and Clairic's own field-extraction prompts) and 3 from wikitext-2.
|
| 62 |
+
|
| 63 |
+

|
| 64 |
+
|
| 65 |
+
## The extraction head
|
| 66 |
+
|
| 67 |
+
Cloudflare's repository also has `clair_head.safetensors`, a small head that reads the model's hidden states and returns typed numbers, dates and spans with confidence scores, null probabilities, and estimate and forecast quantiles. It runs only in Cloudflare's PyTorch runtime (`clairic_model.py`, `systemone`) with the original weights, and it is not in these files. For typed extraction with scores, use [Cloudflare/clairic-flash](https://huggingface.co/Cloudflare/clairic-flash). These files hold the language model and the vision encoder: chat, generation, image input, and extraction answers written as JSON.
|
| 68 |
+
|
| 69 |
+
## How to run
|
| 70 |
+
|
| 71 |
+
```sh
|
| 72 |
+
llama-server -m clairic-flash-Q4_K_M.gguf --mmproj mmproj-clairic-flash-BF16.gguf \
|
| 73 |
+
--jinja -ngl 99 -c 32768 --chat-template-kwargs '{"enable_thinking":false}'
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
Cloudflare's runtime runs the model with thinking off, as above. For JSON that follows a schema, pass the schema in the request (`response_format` with `json_schema` in llama-server, or `--json-schema` in llama-cli); llama.cpp turns it into a grammar.
|
| 77 |
+
|
| 78 |
+
Cloudflare's runtime asks for one field at a time, in one user message, and the model answers with one JSON value:
|
| 79 |
+
|
| 80 |
+
```text
|
| 81 |
+
Extract the requested value from the supplied input, following the field instructions and scope. Return exactly one JSON scalar matching the field schema: quote and escape strings, write numbers without digit-group separators, and use null only when the value is unavailable and null is allowed. Zero is a present number. Preserve repeated source words and list entries. End immediately after the value.
|
| 82 |
+
Field: total
|
| 83 |
+
Schema: {"type":["number","null"]}
|
| 84 |
+
Instructions: The invoice total.
|
| 85 |
+
|
| 86 |
+
Document:
|
| 87 |
+
Invoice from Northwind Supply. Issued 2026-09-02. Items: Pens; Paper. Total: $1080.00.
|
| 88 |
+
```
|
| 89 |
+
|
| 90 |
+
Every quant here answers `1080`, and `"Northwind Supply"` when the field is `vendor`.
|
| 91 |
+
|
| 92 |
+
## How these were made
|
| 93 |
+
|
| 94 |
+
1. Convert Cloudflare's BF16 checkpoint with llama.cpp's `convert_hf_to_gguf.py --no-mtp` (commit `e4b620af19f02960dea7a3a81de7c5805aa3a333`), and the vision encoder with `--mmproj` (BF16). The checkpoint's multi-token-prediction block is left out, as Cloudflare's config turns it off.
|
| 95 |
+
2. Build the importance matrix with `llama-imatrix`: 600 chunks of 4,096 tokens of chat-formatted text rendered with the model's template, thinking off (databricks-dolly-15k in English, KoAlpaca-v1.1a in Korean, python_code_instructions_18k_alpaca for code, gsm8k for math, MasterControlAIML/JSON-Unstructured-Structured for schema-guided JSON, and paraloq/json_data_extraction as Clairic's field-extraction prompts), with `--process-output`.
|
| 96 |
+
3. Make each quant with `llama-quantize --imatrix IM --tensor-type ssm_beta_alpha=f16 <bf16 gguf> <out> <QUANT>` (Q8_0 without the importance matrix): every weight matrix gets llama.cpp's own mix for that type; the Gated DeltaNet beta/alpha projection stays F16 (all but 0.035 % of its BF16 values are exact in F16, the largest difference 3e-8); norms, `ssm_a`, `ssm_dt` and the conv1d kernels stay F32.
|
| 97 |
+
|
| 98 |
+
The model: 8.95B parameters in the language model and 0.46B in the vision encoder; 32 layers (24 Gated DeltaNet linear-attention layers, 8 full-attention layers), 16 query and 4 KV heads of dimension 256, hidden size 4,096, context 262,144, vocabulary 248,320.
|
| 99 |
+
|
| 100 |
+
## License and notices
|
| 101 |
+
|
| 102 |
+
- **License:** Apache-2.0, copied in `LICENSE` (Cloudflare's text).
|
| 103 |
+
- **What we changed:** we quantized the weights and converted them to GGUF.
|
| 104 |
+
- **Notices:** `NOTICE` names the source model and its copyright holders.
|
| 105 |
+
- Xylolabs is not affiliated with or endorsed by Cloudflare.
|
| 106 |
+
|
| 107 |
+
## Cloudflare's original model description
|
| 108 |
+
|
| 109 |
+
This section is Cloudflare's model card, copied from [Cloudflare/clairic-flash](https://huggingface.co/Cloudflare/clairic-flash) (Apache-2.0).
|
| 110 |
+
|
| 111 |
+
- It describes Cloudflare's original model, not these files. Its usage code needs the original weights and Cloudflare's runtime; for the GGUF files, see "How to run" above.
|
| 112 |
+
- We changed only the heading levels (two deeper).
|
| 113 |
+
|
| 114 |
+
### Clairic Flash
|
| 115 |
+
|
| 116 |
+
Clairic Flash is a 9B multimodal model that turns a state and a schema of typed fields
|
| 117 |
+
into structured answers. It supports text and image inputs, extraction, numerical
|
| 118 |
+
estimation, and forecasting. Each field has its own value and scoring information;
|
| 119 |
+
the response also reports input truncation and token usage.
|
| 120 |
+
|
| 121 |
+
See [Clairic](https://huggingface.co/Cloudflare/clairic) for the other model
|
| 122 |
+
in the Clairic family.
|
| 123 |
+
|
| 124 |
+
#### Model
|
| 125 |
+
|
| 126 |
+
- **Base model:** [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B).
|
| 127 |
+
- **Inputs:** a text or JSON state, optional images, and a mapping of field names to specifications.
|
| 128 |
+
- **Outputs:** typed values, lists, nulls, estimates, and forecast paths.
|
| 129 |
+
- **Scoring:** extraction confidence and null probabilities, plus optional quantiles for estimates.
|
| 130 |
+
- **Runtime:** PyTorch and Transformers, with local Python request helpers.
|
| 131 |
+
|
| 132 |
+
#### Usage
|
| 133 |
+
|
| 134 |
+
Use Python 3.11 or later and install the packages listed in `requirements.txt`. Inference uses PyTorch and
|
| 135 |
+
Transformers; `xgrammar` supplies schema constraints through a Transformers logits
|
| 136 |
+
processor.
|
| 137 |
+
|
| 138 |
+
Download the repository, load the model and processor, and call `systemone` with a
|
| 139 |
+
System One: Extract request.
|
| 140 |
+
|
| 141 |
+
```python
|
| 142 |
+
import sys
|
| 143 |
+
|
| 144 |
+
from huggingface_hub import snapshot_download
|
| 145 |
+
|
| 146 |
+
path = snapshot_download("Cloudflare/clairic-flash")
|
| 147 |
+
sys.path.insert(0, path)
|
| 148 |
+
from clairic_model import load_release_model, systemone
|
| 149 |
+
|
| 150 |
+
model, processor = load_release_model(path, device="cuda")
|
| 151 |
+
|
| 152 |
+
response = systemone(
|
| 153 |
+
model,
|
| 154 |
+
processor,
|
| 155 |
+
{
|
| 156 |
+
"state": (
|
| 157 |
+
"Invoice from Northwind Supply. Issued 2026-09-02. "
|
| 158 |
+
"Items: Pens; Paper. Total: $1080.00."
|
| 159 |
+
),
|
| 160 |
+
"fields": {
|
| 161 |
+
"vendor": {"type": "text", "instructions": "The invoice vendor."},
|
| 162 |
+
"total": {"type": "number", "decimals": 2},
|
| 163 |
+
"issued": {"type": "date"},
|
| 164 |
+
"items": {
|
| 165 |
+
"type": "list",
|
| 166 |
+
"items": "text",
|
| 167 |
+
"instructions": "The purchased item names, in order.",
|
| 168 |
+
},
|
| 169 |
+
},
|
| 170 |
+
},
|
| 171 |
+
)
|
| 172 |
+
print(response["answers"])
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
##### Images
|
| 176 |
+
|
| 177 |
+
Pass PIL images alongside the state. Embedded base64 image inputs are also accepted.
|
| 178 |
+
|
| 179 |
+
```python
|
| 180 |
+
from PIL import Image
|
| 181 |
+
|
| 182 |
+
response = systemone(
|
| 183 |
+
model,
|
| 184 |
+
processor,
|
| 185 |
+
{
|
| 186 |
+
"state": "Read the attached receipt.",
|
| 187 |
+
"images": [Image.open("receipt.png")],
|
| 188 |
+
"fields": {
|
| 189 |
+
"merchant": {"type": "text", "instructions": "The merchant name."},
|
| 190 |
+
"total": {"type": "number", "decimals": 2},
|
| 191 |
+
},
|
| 192 |
+
},
|
| 193 |
+
)
|
| 194 |
+
print(response["answers"])
|
| 195 |
+
```
|
| 196 |
+
|
| 197 |
+
##### Estimates and forecasts
|
| 198 |
+
|
| 199 |
+
Declare a range for estimated values. Forecasts also specify a horizon and interval.
|
| 200 |
+
Set `include_quantiles` to return the available quantiles.
|
| 201 |
+
|
| 202 |
+
```python
|
| 203 |
+
response = systemone(
|
| 204 |
+
model,
|
| 205 |
+
processor,
|
| 206 |
+
{
|
| 207 |
+
"state": "Daily demand for the last seven days: 41, 45, 43, 47, 49, 46, 48.",
|
| 208 |
+
"fields": {
|
| 209 |
+
"next_day": {"type": "estimate", "min": 0, "max": 100},
|
| 210 |
+
"next_three_days": {
|
| 211 |
+
"type": "forecast",
|
| 212 |
+
"min": 0,
|
| 213 |
+
"max": 100,
|
| 214 |
+
"horizon": 3,
|
| 215 |
+
"interval": "day",
|
| 216 |
+
},
|
| 217 |
+
},
|
| 218 |
+
"options": {"include_quantiles": True},
|
| 219 |
+
},
|
| 220 |
+
)
|
| 221 |
+
print(response["answers"])
|
| 222 |
+
```
|
| 223 |
+
|
| 224 |
+
#### Input format
|
| 225 |
+
|
| 226 |
+
| Field | Description |
|
| 227 |
+
|---|---|
|
| 228 |
+
| `model` | Optional `clairic-flash` or `@cf/cloudflare/clairic-flash` |
|
| 229 |
+
| `state` | Source text; the Python helper serializes JSON values to text |
|
| 230 |
+
| `images` | Optional PIL images or embedded base64 images |
|
| 231 |
+
| `documents` | Optional embedded PDF data URIs or `content_type` / `base64` objects |
|
| 232 |
+
| `fields` | Mapping of output field names to typed specifications |
|
| 233 |
+
| `reference_date` | Optional ISO date for relative date instructions |
|
| 234 |
+
| `options.include_quantiles` | Include available estimate and forecast quantiles |
|
| 235 |
+
| `options.return_state_text` | Include the retained source text in the response |
|
| 236 |
+
|
| 237 |
+
Field specifications support `text`, `number`, `date`, `time`, `datetime`, `duration`,
|
| 238 |
+
`boolean`, `enum`, `object`, `list`, `compute`, `estimate`, and `forecast`.
|
| 239 |
+
`instructions` describes what to return. Numeric fields can specify units and
|
| 240 |
+
rounding; lists declare their item schema; estimates and forecasts require bounds.
|
| 241 |
+
`nullable` defaults to true. `source_only: true` selects literal printed numbers,
|
| 242 |
+
dates, times, datetimes, or number/date lists. `knowledge: true` permits knowledge
|
| 243 |
+
answers for text, numbers, and supported list children. `compute` selects the typed
|
| 244 |
+
numeric head. Unsupported options and invalid combinations are rejected.
|
| 245 |
+
|
| 246 |
+
Embedded inputs are limited to 4 MiB each and 8 MiB combined. Images and rendered
|
| 247 |
+
PDF pages share a four-image/page limit. Image `rotation` accepts 0, 90, 180, or 270
|
| 248 |
+
clockwise degrees after EXIF orientation. Remote media URLs are not accepted.
|
| 249 |
+
|
| 250 |
+
#### Response
|
| 251 |
+
|
| 252 |
+
`systemone` returns a dictionary with `model`, `answers`, `truncated`, and `usage`.
|
| 253 |
+
Answers are keyed by the requested field names. Generated scalar extraction answers
|
| 254 |
+
retain `valid`, `complete`, full-sequence `confidence`, and independently scored `p_null`.
|
| 255 |
+
Uniquely matched text evidence includes character spans in `state`; image-only or
|
| 256 |
+
ambiguous evidence has null spans. Lists preserve item order and duplicates.
|
| 257 |
+
Estimates and forecasts include their typed values and, when requested, quantiles.
|
| 258 |
+
|
| 259 |
+
Scores are model probabilities and should be evaluated for the application's own
|
| 260 |
+
acceptance thresholds. Inspect `truncated` and any answer completeness indicators
|
| 261 |
+
before relying on a result.
|
| 262 |
+
|
| 263 |
+
Usage includes retries and supplemental work. The response model ID is `clairic-flash`.
|
| 264 |
+
The Python API raises validation or request errors for invalid inputs, a queue-full
|
| 265 |
+
error for simultaneous requests, and an inference error for failed generation.
|
| 266 |
+
Use `await model.predict_async(request)` in an async application; cancellation
|
| 267 |
+
drains owned work before admitting another request.
|
| 268 |
+
|
| 269 |
+
#### Files
|
| 270 |
+
|
| 271 |
+
| File | Purpose |
|
| 272 |
+
|---|---|
|
| 273 |
+
| `model*.safetensors`, `model.safetensors.index.json`, `config.json` | Model weights and configuration |
|
| 274 |
+
| `clair_head.safetensors`, `clair_head_config.json` | Typed output components |
|
| 275 |
+
| `clairic_model.py` and supporting Python modules | Transformers loading and request handling |
|
| 276 |
+
| Tokenizer and processor files | Text and image preprocessing |
|
| 277 |
+
| `requirements.txt` | Python dependencies |
|
| 278 |
+
| `LICENSE` | Apache-2.0 license |
|
| 279 |
+
|
| 280 |
+
#### License
|
| 281 |
+
|
| 282 |
+
Released under the Apache-2.0 license.
|
kl.png
ADDED
|
Git LFS Details
|