Instructions to use simonfxr/turnsense.cpp-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 simonfxr/turnsense.cpp-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 simonfxr/turnsense.cpp-GGUF:F32 # Run inference directly in the terminal: llama cli -hf simonfxr/turnsense.cpp-GGUF:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf simonfxr/turnsense.cpp-GGUF:F32 # Run inference directly in the terminal: llama cli -hf simonfxr/turnsense.cpp-GGUF:F32
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf simonfxr/turnsense.cpp-GGUF:F32 # Run inference directly in the terminal: ./llama-cli -hf simonfxr/turnsense.cpp-GGUF:F32
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf simonfxr/turnsense.cpp-GGUF:F32 # Run inference directly in the terminal: ./build/bin/llama-cli -hf simonfxr/turnsense.cpp-GGUF:F32
Use Docker
docker model run hf.co/simonfxr/turnsense.cpp-GGUF:F32
- LM Studio
- Jan
- Ollama
How to use simonfxr/turnsense.cpp-GGUF with Ollama:
ollama run hf.co/simonfxr/turnsense.cpp-GGUF:F32
- Unsloth Desktop
- Docker Model Runner
How to use simonfxr/turnsense.cpp-GGUF with Docker Model Runner:
docker model run hf.co/simonfxr/turnsense.cpp-GGUF:F32
- Lemonade
How to use simonfxr/turnsense.cpp-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull simonfxr/turnsense.cpp-GGUF:F32
Run and chat with the model
lemonade run user.turnsense.cpp-GGUF-F32
List all available models
lemonade list
- Atomic Chat
Add TurnSense.cpp GGUF model card and licensing
Browse files
LICENSE
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
|
| 10 |
+
|
| 11 |
+
"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
|
| 12 |
+
|
| 13 |
+
"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
|
| 14 |
+
|
| 15 |
+
"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
|
| 16 |
+
|
| 17 |
+
"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
|
| 18 |
+
|
| 19 |
+
"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
|
| 20 |
+
|
| 21 |
+
"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
|
| 22 |
+
|
| 23 |
+
"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
|
| 24 |
+
|
| 25 |
+
"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
|
| 26 |
+
|
| 27 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
|
| 28 |
+
|
| 29 |
+
2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
|
| 30 |
+
|
| 31 |
+
3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
|
| 32 |
+
|
| 33 |
+
4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
|
| 34 |
+
|
| 35 |
+
(a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
|
| 36 |
+
|
| 37 |
+
(b) You must cause any modified files to carry prominent notices stating that You changed the files; and
|
| 38 |
+
|
| 39 |
+
(c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
|
| 40 |
+
|
| 41 |
+
(d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
|
| 42 |
+
|
| 43 |
+
You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
|
| 44 |
+
|
| 45 |
+
5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
|
| 46 |
+
|
| 47 |
+
6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
|
| 48 |
+
|
| 49 |
+
7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
|
| 50 |
+
|
| 51 |
+
8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
|
| 52 |
+
|
| 53 |
+
9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
|
| 54 |
+
|
| 55 |
+
END OF TERMS AND CONDITIONS
|
| 56 |
+
|
| 57 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 58 |
+
|
| 59 |
+
To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
|
| 60 |
+
|
| 61 |
+
Copyright [yyyy] [name of copyright owner]
|
| 62 |
+
|
| 63 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 64 |
+
you may not use this file except in compliance with the License.
|
| 65 |
+
You may obtain a copy of the License at
|
| 66 |
+
|
| 67 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 68 |
+
|
| 69 |
+
Unless required by applicable law or agreed to in writing, software
|
| 70 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 71 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 72 |
+
See the License for the specific language governing permissions and
|
| 73 |
+
limitations under the License.
|
NOTICE
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
TurnSense.cpp GGUF model artifacts
|
| 2 |
+
|
| 3 |
+
Derived from the TurnSense model by Latisha Besariani Hendra:
|
| 4 |
+
https://huggingface.co/latishab/turnsense
|
| 5 |
+
|
| 6 |
+
The artifacts contain deterministic format conversion, LoRA merging, and
|
| 7 |
+
selective Q8_0 quantization changes. See README.md for exact provenance.
|
README.md
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model: latishab/turnsense
|
| 6 |
+
base_model_relation: quantized
|
| 7 |
+
pipeline_tag: text-classification
|
| 8 |
+
library_name: ggml
|
| 9 |
+
tags:
|
| 10 |
+
- gguf
|
| 11 |
+
- ggml
|
| 12 |
+
- turn-taking
|
| 13 |
+
- end-of-utterance
|
| 14 |
+
- voice-agents
|
| 15 |
+
- text-classification
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# TurnSense.cpp GGUF
|
| 19 |
+
|
| 20 |
+
Canonical F32 and selective Q8_0 GGUF artifacts for
|
| 21 |
+
[TurnSense.cpp](https://github.com/simonfxr/turnsense.cpp), a native C/C++
|
| 22 |
+
end-of-utterance classifier built on official upstream ggml.
|
| 23 |
+
|
| 24 |
+
These files are converted from
|
| 25 |
+
[`latishab/turnsense`](https://huggingface.co/latishab/turnsense) at immutable
|
| 26 |
+
revision `1ddc8f679abf3d9a42a93373b0e709f0c9d7fe63`. The model architecture and
|
| 27 |
+
weights are unchanged except for deterministic LoRA merging and, for the Q8_0
|
| 28 |
+
artifact, weight quantization. The production runtime has no ONNX Runtime or
|
| 29 |
+
Python dependency.
|
| 30 |
+
|
| 31 |
+
## Files
|
| 32 |
+
|
| 33 |
+
| File | Purpose | Size | SHA-256 |
|
| 34 |
+
|---|---|---:|---|
|
| 35 |
+
| `turnsense-q8_0.gguf` | Recommended CPU/Vulkan runtime model | 145,012,704 bytes | `e978f2462e1887c2959173066e2f534f3c02fea686323bfc454aa37842970966` |
|
| 36 |
+
| `turnsense-f32.gguf` | Canonical conversion and quantization source | 540,047,168 bytes | `0eb7d0ea7bccbcd2f9aa4b722ee202efbf53b4e430ba90c527548f8578d2460e` |
|
| 37 |
+
|
| 38 |
+
`SHA256SUMS` contains the same checksums in machine-readable form.
|
| 39 |
+
|
| 40 |
+
## Q8_0 policy
|
| 41 |
+
|
| 42 |
+
The Q8_0 artifact is produced from the canonical F32 GGUF with the native
|
| 43 |
+
`turnsense_quantize` tool and upstream `ggml_quantize_chunk`:
|
| 44 |
+
|
| 45 |
+
- **Q8_0:** `token_embd.weight` and all 210 transformer attention/FFN
|
| 46 |
+
projection matrices.
|
| 47 |
+
- **F32:** all 61 RMS normalization vectors and `classifier.weight`.
|
| 48 |
+
|
| 49 |
+
This quantizes 211 tensors and retains 62 tensors as F32. Tensor payload drops
|
| 50 |
+
from 513.14 MiB to 136.40 MiB, a 3.76x reduction. Repeated conversion produces
|
| 51 |
+
a byte-identical Q8_0 file. The runtime validates this policy exactly and
|
| 52 |
+
rejects incompatible layouts.
|
| 53 |
+
|
| 54 |
+
The dynamically quantized upstream ONNX model is **not** the source of this
|
| 55 |
+
Q8_0 artifact.
|
| 56 |
+
|
| 57 |
+
## Usage
|
| 58 |
+
|
| 59 |
+
Download the recommended model:
|
| 60 |
+
|
| 61 |
+
```bash
|
| 62 |
+
hf download simonfxr/turnsense.cpp-GGUF turnsense-q8_0.gguf \
|
| 63 |
+
--local-dir models
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
Build and run the native runtime:
|
| 67 |
+
|
| 68 |
+
```bash
|
| 69 |
+
git clone --recurse-submodules https://github.com/simonfxr/turnsense.cpp.git
|
| 70 |
+
cd turnsense.cpp
|
| 71 |
+
cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release
|
| 72 |
+
cmake --build build -j
|
| 73 |
+
|
| 74 |
+
./build/turnsense_cli \
|
| 75 |
+
--model models/turnsense-q8_0.gguf \
|
| 76 |
+
--backend cpu \
|
| 77 |
+
--json "Could you send that report tomorrow?"
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
Use `--backend vulkan` for the Vulkan backend. The stable C API is documented
|
| 81 |
+
in the [source repository README](https://github.com/simonfxr/turnsense.cpp#c-api).
|
| 82 |
+
|
| 83 |
+
TurnSense operates on text, not audio. A voice agent should evaluate the latest
|
| 84 |
+
punctuated STT transcript at candidate pauses and combine `prob_eou` with VAD,
|
| 85 |
+
latency, and product policy.
|
| 86 |
+
|
| 87 |
+
## Validation
|
| 88 |
+
|
| 89 |
+
The runtime graph uses official ggml operations and optimized backend kernels.
|
| 90 |
+
For Q8_0, it verifies that every quantized `get_rows` and `mul_mat` node remains
|
| 91 |
+
on the selected CPU or Vulkan backend rather than unexpectedly falling back.
|
| 92 |
+
|
| 93 |
+
Measured maximum absolute probability differences on the bundled seven-case
|
| 94 |
+
fixture suite:
|
| 95 |
+
|
| 96 |
+
| Backend / artifact | Reference | Maximum delta | Classifications |
|
| 97 |
+
|---|---|---:|---|
|
| 98 |
+
| CPU F32 | FP32 ONNX Runtime | `9.84e-7` | identical |
|
| 99 |
+
| Vulkan F32 | FP32 ONNX Runtime | `5.69e-4` | identical |
|
| 100 |
+
| CPU Q8_0 | native CPU F32 | `0.04161` | identical |
|
| 101 |
+
| Vulkan Q8_0 | native Vulkan F32 | `0.01413` | identical |
|
| 102 |
+
|
| 103 |
+
Vulkan was validated on an AMD Radeon RX 7900 XTX. Backend floating-point
|
| 104 |
+
accumulation is not expected to be bit-identical.
|
| 105 |
+
|
| 106 |
+
## Prompt and labels
|
| 107 |
+
|
| 108 |
+
The runtime prepends the literal prompt prefix `<|user|> ` and applies the
|
| 109 |
+
embedded GPT-2 byte-level BPE tokenizer. Do not append `<|im_end|>`.
|
| 110 |
+
|
| 111 |
+
- Label `0`: `NON_EOU`
|
| 112 |
+
- Label `1`: `EOU`
|
| 113 |
+
|
| 114 |
+
Applications should normally use `prob_eou` with a product-specific threshold
|
| 115 |
+
rather than treating argmax as a fixed policy.
|
| 116 |
+
|
| 117 |
+
## Limitations
|
| 118 |
+
|
| 119 |
+
- The upstream model is English-focused.
|
| 120 |
+
- Predictions are sensitive to punctuation and STT transcript quality.
|
| 121 |
+
- Turn-taking decisions should also incorporate VAD, timing, and application
|
| 122 |
+
context.
|
| 123 |
+
- The fixture suite validates conversion parity; it is not a broad task-quality
|
| 124 |
+
benchmark.
|
| 125 |
+
- This model is not intended for safety-critical decisions.
|
| 126 |
+
|
| 127 |
+
## Provenance
|
| 128 |
+
|
| 129 |
+
- Upstream source: <https://github.com/latishab/turnsense>
|
| 130 |
+
- Upstream source revision: `b40a25b4da94c961b64393752e507f59295061ad`
|
| 131 |
+
- Upstream model: <https://huggingface.co/latishab/turnsense>
|
| 132 |
+
- Upstream model revision: `1ddc8f679abf3d9a42a93373b0e709f0c9d7fe63`
|
| 133 |
+
- Runtime source: <https://github.com/simonfxr/turnsense.cpp>
|
| 134 |
+
|
| 135 |
+
Full source artifact hashes and deterministic conversion instructions are in
|
| 136 |
+
[`docs/model-provenance.md`](https://github.com/simonfxr/turnsense.cpp/blob/main/docs/model-provenance.md).
|
| 137 |
+
|
| 138 |
+
## License
|
| 139 |
+
|
| 140 |
+
The model artifacts are distributed under the Apache License 2.0, matching the
|
| 141 |
+
upstream TurnSense model. See `LICENSE`. The TurnSense.cpp runtime source is
|
| 142 |
+
separately distributed under the MIT License.
|
SHA256SUMS
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
e978f2462e1887c2959173066e2f534f3c02fea686323bfc454aa37842970966 turnsense-q8_0.gguf
|
| 2 |
+
0eb7d0ea7bccbcd2f9aa4b722ee202efbf53b4e430ba90c527548f8578d2460e turnsense-f32.gguf
|