Instructions to use zaindanaharper/flywheel-local-coder-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use zaindanaharper/flywheel-local-coder-14b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="zaindanaharper/flywheel-local-coder-14b", filename="telos-coder-14b-cpt2020-q4_k_m.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use zaindanaharper/flywheel-local-coder-14b 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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M # Run inference directly in the terminal: llama cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M # Run inference directly in the terminal: llama cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
Use Docker
docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use zaindanaharper/flywheel-local-coder-14b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zaindanaharper/flywheel-local-coder-14b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zaindanaharper/flywheel-local-coder-14b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
- Ollama
How to use zaindanaharper/flywheel-local-coder-14b with Ollama:
ollama run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
- Unsloth Studio
How to use zaindanaharper/flywheel-local-coder-14b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for zaindanaharper/flywheel-local-coder-14b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for zaindanaharper/flywheel-local-coder-14b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for zaindanaharper/flywheel-local-coder-14b to start chatting
- Pi
How to use zaindanaharper/flywheel-local-coder-14b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "zaindanaharper/flywheel-local-coder-14b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use zaindanaharper/flywheel-local-coder-14b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zaindanaharper/flywheel-local-coder-14b: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://127.0.0.1:8080/v1 hermes config set model.default zaindanaharper/flywheel-local-coder-14b:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use zaindanaharper/flywheel-local-coder-14b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zaindanaharper/flywheel-local-coder-14b: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://127.0.0.1:8080/v1 \ --custom-model-id "zaindanaharper/flywheel-local-coder-14b: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"
- Docker Model Runner
How to use zaindanaharper/flywheel-local-coder-14b with Docker Model Runner:
docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
- Lemonade
How to use zaindanaharper/flywheel-local-coder-14b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull zaindanaharper/flywheel-local-coder-14b:Q4_K_M
Run and chat with the model
lemonade run user.flywheel-local-coder-14b-Q4_K_M
List all available models
lemonade list
Model card, license, provenance chain, and receipts
Browse files- LICENSE +209 -0
- MODEL_CARD.md +46 -0
- Modelfile +1 -0
- README.md +45 -0
- benchmark-summary.json +39 -0
- checksums.sha256 +11 -0
- endpoint.json +62 -0
- provenance.json +36 -0
- release-checklist.md +18 -0
- safety.md +25 -0
- usage.md +42 -0
LICENSE
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright [yyyy] [name of copyright owner]
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
| 202 |
+
|
| 203 |
+
================================================================
|
| 204 |
+
|
| 205 |
+
ATTRIBUTION
|
| 206 |
+
|
| 207 |
+
This artifact is a derivative of Qwen2.5-Coder-14B-Instruct
|
| 208 |
+
(Copyright Alibaba Cloud, Apache-2.0), merged with a locally trained
|
| 209 |
+
QLoRA continued-pretraining adapter (checkpoint-2020).
|
MODEL_CARD.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Flywheel-Local-Coder-14B Model Card
|
| 2 |
+
|
| 3 |
+
Status: draft, not publish-ready. Identity and provenance are verified; benchmark evidence is pending.
|
| 4 |
+
|
| 5 |
+
## Model identity
|
| 6 |
+
|
| 7 |
+
- Release name: `Flywheel-Local-Coder-14B`
|
| 8 |
+
- Artifact file: `telos-coder-14b-cpt2020-q4_k_m.gguf`
|
| 9 |
+
- Base model: `Qwen2.5-Coder-14B-Instruct` (Alibaba Cloud / Qwen team, Apache-2.0)
|
| 10 |
+
- Adapter: `checkpoint-2020`, QLoRA continued pretraining, train_loss 0.035
|
| 11 |
+
- Composition: base weights merged with the adapter, then quantized
|
| 12 |
+
- Quantization: Q4_K_M (GGUF)
|
| 13 |
+
- Size: 8,988,110,880 bytes
|
| 14 |
+
- Artifact SHA-256: `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be`
|
| 15 |
+
- Adapter SHA-256: `4de07c6ea342d1cc200d4a6e2b28a63f6ee37f34c5c0926c35d8c7db74d38d0f`
|
| 16 |
+
- LoRA GGUF SHA-256: `c89091709d7f385226000091dca976b7ce68086255e78af96599d06b6b52f547`
|
| 17 |
+
- Artifact location: `E:\local-model-run\release\flywheel-local-coder-14b\telos-coder-14b-cpt2020-q4_k_m.gguf`
|
| 18 |
+
- Local serving name: Ollama `flywheel-local-coder-14b`
|
| 19 |
+
- Manifest: `C:\dev\local-model\tasks\research\gguf_ship_manifest_checkpoint2020.json` (schema `telos.model-artifact/v1`)
|
| 20 |
+
|
| 21 |
+
## Training data
|
| 22 |
+
|
| 23 |
+
Continued pretraining on the operator's `C:\dev` ecosystem corpus. Pack numbers (verified in `HANDOFF.md` and `E:\local-model-run\data\packed\PACK_COMPLETE.json`): 66,158,592 tokens, 8 shards, 16,152 sequences, seq_len 4096, from 17,997 corpus files. Corpus content hash `68345cdc6667f20d1678ac0a9139edc170348dfdebb9ae6045cde3d204f4fe62`; pack shards hash `018798dfce7d4c86f5a6ea502a383553220f2e76facfe76acbe52b1c278ae543`. Dataset receipt: `tasks/research/dataset_receipt_checkpoint2020.json`. Corpus source identifiers stay proprietary.
|
| 24 |
+
|
| 25 |
+
## Intended use
|
| 26 |
+
|
| 27 |
+
Local-first agentic coding inside the flywheel harness, served via Ollama or llama.cpp on the operator's Windows machine. Receipts, endpoint gates, and benchmark evidence are required before any wider publication.
|
| 28 |
+
|
| 29 |
+
## Limitations
|
| 30 |
+
|
| 31 |
+
- Q4_K_M quantization; quantization loss relative to the merged fp16 weights is not measured.
|
| 32 |
+
- Built and tested for Windows local serving only.
|
| 33 |
+
- No benchmark evidence exists yet. Benchmarks are pending. No capability uplift over the base model is claimed.
|
| 34 |
+
- Deterministic smoke (llama-completion, temp 0, seed 7, byte-identical reruns, MATCH) is the only behavioral evidence recorded.
|
| 35 |
+
|
| 36 |
+
## License
|
| 37 |
+
|
| 38 |
+
Apache-2.0 derivative. Base model `Qwen2.5-Coder-14B-Instruct` is Copyright Alibaba Cloud, Apache-2.0. This artifact merges a locally trained QLoRA adapter into those weights and retains the Apache-2.0 license with attribution. See the LICENSE file shipped next to the artifact.
|
| 39 |
+
|
| 40 |
+
## Current benchmark status
|
| 41 |
+
|
| 42 |
+
Benchmarks are pending. No benchmark result is recorded for this artifact.
|
| 43 |
+
|
| 44 |
+
## Current publication verdict
|
| 45 |
+
|
| 46 |
+
Do not publish. Blocked on benchmark evidence, endpoint gate history, and explicit operator approval.
|
Modelfile
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
FROM E:\local-model-run\release\flywheel-local-coder-14b\telos-coder-14b-cpt2020-q4_k_m.gguf
|
README.md
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- code
|
| 6 |
+
- gguf
|
| 7 |
+
- qlora
|
| 8 |
+
- local-first
|
| 9 |
+
- verified-inference
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
+
library_name: gguf
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Flywheel-Local-Coder-14B Release README
|
| 15 |
+
|
| 16 |
+
Status: staged, awaiting operator upload approval. Trained artifact, endpoint gate evidence, and first benchmark evidence exist.
|
| 17 |
+
|
| 18 |
+
## What this release is
|
| 19 |
+
|
| 20 |
+
`Flywheel-Local-Coder-14B` is the release name for a trained 14B artifact:
|
| 21 |
+
|
| 22 |
+
- Artifact file: `telos-coder-14b-cpt2020-q4_k_m.gguf` (Q4_K_M GGUF, 8,988,110,880 bytes).
|
| 23 |
+
- SHA-256: `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be`
|
| 24 |
+
- Identity: base `Qwen2.5-Coder-14B-Instruct` merged with QLoRA continued-pretraining adapter `checkpoint-2020` (train_loss 0.035), then quantized to Q4_K_M.
|
| 25 |
+
- Artifact location: `E:\local-model-run\release\flywheel-local-coder-14b\telos-coder-14b-cpt2020-q4_k_m.gguf`
|
| 26 |
+
- Local serving: Ollama model name `flywheel-local-coder-14b`, created from the Modelfile in the same directory.
|
| 27 |
+
|
| 28 |
+
## What evidence exists
|
| 29 |
+
|
| 30 |
+
- Provenance chain, recorded in `C:\dev\local-model\tasks\research\gguf_ship_manifest_checkpoint2020.json`, each layer re-derivable:
|
| 31 |
+
- corpus_content_hash `68345cdc6667f20d1678ac0a9139edc170348dfdebb9ae6045cde3d204f4fe62` (17,997 corpus files)
|
| 32 |
+
- pack_shards_hash `018798dfce7d4c86f5a6ea502a383553220f2e76facfe76acbe52b1c278ae543`
|
| 33 |
+
- checkpoint_adapter_sha256 `4de07c6ea342d1cc200d4a6e2b28a63f6ee37f34c5c0926c35d8c7db74d38d0f`
|
| 34 |
+
- GGUF sha256 `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be`
|
| 35 |
+
- Deterministic smoke: `llama-completion` at temp 0, seed 7, byte-identical reruns (MATCH). Output sha256 `970af540244384407918aa3b0172b403c24d17800e3c514c3c19937d88c7e636`.
|
| 36 |
+
|
| 37 |
+
## What is still missing
|
| 38 |
+
|
| 39 |
+
- Benchmark evidence. No benchmark has been run against this artifact. All benchmark claims are pending. No capability uplift over the base model is claimed.
|
| 40 |
+
- Endpoint gate history (`harness.model-endpoint-gate/v1` artifacts attached to the release row).
|
| 41 |
+
- Explicit operator approval for upload. Never auto-approved.
|
| 42 |
+
|
| 43 |
+
## Publication rule
|
| 44 |
+
|
| 45 |
+
This release stays blocked until every gate in `RELEASE-CHECKLIST.md` is satisfied by artifact paths, not narrative claims.
|
benchmark-summary.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"benchmark_artifact_count": 4,
|
| 3 |
+
"benchmark_artifacts": [
|
| 4 |
+
{
|
| 5 |
+
"content_read": false,
|
| 6 |
+
"name": "flywheel-local-coder-14b-benchmark-ci.json",
|
| 7 |
+
"path": "C:\\dev\\local-model\\artifacts\\flywheel-local-coder-14b-benchmark-ci.json",
|
| 8 |
+
"size_bytes": 2222,
|
| 9 |
+
"suffix": ".json"
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"content_read": false,
|
| 13 |
+
"name": "flywheel-local-coder-14b-benchmark-ci.md",
|
| 14 |
+
"path": "C:\\dev\\local-model\\artifacts\\flywheel-local-coder-14b-benchmark-ci.md",
|
| 15 |
+
"size_bytes": 992,
|
| 16 |
+
"suffix": ".md"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"content_read": false,
|
| 20 |
+
"name": "flywheel-local-coder-14b-benchmark-m7-hard-scorecard.json",
|
| 21 |
+
"path": "C:\\dev\\local-model\\artifacts\\flywheel-local-coder-14b-benchmark-m7-hard-scorecard.json",
|
| 22 |
+
"size_bytes": 1226,
|
| 23 |
+
"suffix": ".json"
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"content_read": false,
|
| 27 |
+
"name": "flywheel-local-coder-14b-benchmark-m7-scorecard.json",
|
| 28 |
+
"path": "C:\\dev\\local-model\\artifacts\\flywheel-local-coder-14b-benchmark-m7-scorecard.json",
|
| 29 |
+
"size_bytes": 1221,
|
| 30 |
+
"suffix": ".json"
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"candidate_name": "Flywheel-Local-Coder-14B",
|
| 34 |
+
"generated_utc": "2026-07-09T20:32:36.042999Z",
|
| 35 |
+
"model": "14B",
|
| 36 |
+
"note": "Benchmark execution is intentionally separate from repository staging.",
|
| 37 |
+
"schema": "harness.model-repo-stage.benchmark-summary/v1",
|
| 38 |
+
"status": "BENCHMARK_EVIDENCE_ATTACHED"
|
| 39 |
+
}
|
checksums.sha256
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2af5ee89816a9b703f6a2bf5cb42a0d83aee699904bb5f7ca89981e62cde72b8 LICENSE
|
| 2 |
+
6d9f6ff635f6f0793ec2dbec67a54fb00a9c5e2cc0244da27ea3a480d3e57669 MODEL_CARD.md
|
| 3 |
+
89deb42a68f75c3706a742b7cc5a6cdcc1125025a626a4bbdbb0584d5e4a9e40 README.md
|
| 4 |
+
1e8ee7e5c08c1e1b8f0699b44250d8c5fbdc794ad546958348a37a7586f35c9c WEIGHT-CHECKSUMS-PENDING.md
|
| 5 |
+
24bc5108d3d550e7835852e18705c48ecf45e13d87532a35c6f8379e4e22d5b7 benchmark-summary.json
|
| 6 |
+
958764b5464c37a9f2a12544663ad27882a471855a562de96adb4dbfcd5370e1 endpoint.json
|
| 7 |
+
ced7c4545b433756704b7c00a780d8cbe97c7b6ca529a4a7b4d16fa0b2a455bd provenance.json
|
| 8 |
+
55aff1c68e3ea175d36a0ebb34d97da5e5e8951e155e3fae83d9370eb9541275 release-checklist.md
|
| 9 |
+
92ec7167cf750000034fd63512f4b9fa8ae2159207dfa5e8f88aefd1ee04bf54 safety.md
|
| 10 |
+
613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be telos-coder-14b-cpt2020-q4_k_m.gguf
|
| 11 |
+
3ff5ab42283f72d64c26ee7aacf280556cffc65d14a47e5f553ac7eddd9ec95c usage.md
|
endpoint.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"candidate_name": "Flywheel-Local-Coder-14B",
|
| 3 |
+
"endpoint_gate_generation_ok_count": 1,
|
| 4 |
+
"endpoint_gate_rows": [
|
| 5 |
+
{
|
| 6 |
+
"backend": "ollama",
|
| 7 |
+
"failure_class": "endpoint_error",
|
| 8 |
+
"generation_ok": false,
|
| 9 |
+
"health_ok": true,
|
| 10 |
+
"profile_id": "ollama-14b",
|
| 11 |
+
"provider_role": "ollama_local",
|
| 12 |
+
"quality_score": 0.0,
|
| 13 |
+
"receipt_hash": "f151e2702024952fe9fc78488a6b1b731b228406bb3465f12c6313506bac7715"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"backend": "ollama",
|
| 17 |
+
"failure_class": "",
|
| 18 |
+
"generation_ok": true,
|
| 19 |
+
"health_ok": true,
|
| 20 |
+
"profile_id": "ollama-release-14b",
|
| 21 |
+
"provider_role": "ollama_local",
|
| 22 |
+
"quality_score": 1.0,
|
| 23 |
+
"receipt_hash": "1dd9849a468be4369eb1eb5313578e9757ccf506cb3fc02b58f7c3bec6658dee"
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"endpoint_profiles": [
|
| 27 |
+
{
|
| 28 |
+
"agentic_backend": "harness.local_agent.ServeBackend",
|
| 29 |
+
"backend": "serve",
|
| 30 |
+
"content_read": false,
|
| 31 |
+
"endpoint_url": "http://127.0.0.1:8765",
|
| 32 |
+
"live_probed": false,
|
| 33 |
+
"profile_id": "serve-14b",
|
| 34 |
+
"provider_role": "flywheel",
|
| 35 |
+
"root_exists": true
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"agentic_backend": "harness.local_agent.OllamaBackend",
|
| 39 |
+
"backend": "ollama",
|
| 40 |
+
"content_read": false,
|
| 41 |
+
"endpoint_url": "http://127.0.0.1:11434",
|
| 42 |
+
"live_probed": false,
|
| 43 |
+
"profile_id": "ollama-14b",
|
| 44 |
+
"provider_role": "ollama_local",
|
| 45 |
+
"root_exists": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"agentic_backend": "harness.local_agent.OllamaBackend",
|
| 49 |
+
"backend": "ollama",
|
| 50 |
+
"content_read": false,
|
| 51 |
+
"endpoint_url": "http://127.0.0.1:11434",
|
| 52 |
+
"live_probed": false,
|
| 53 |
+
"profile_id": "ollama-release-14b",
|
| 54 |
+
"provider_role": "ollama_local",
|
| 55 |
+
"root_exists": true
|
| 56 |
+
}
|
| 57 |
+
],
|
| 58 |
+
"generated_utc": "2026-07-09T20:32:36.042999Z",
|
| 59 |
+
"model": "14B",
|
| 60 |
+
"publication_note": "Endpoint profiles are local defaults. Public upload remains blocked until endpoint generation gates pass.",
|
| 61 |
+
"schema": "harness.model-repo-stage.endpoint/v1"
|
| 62 |
+
}
|
provenance.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"candidate_name": "Flywheel-Local-Coder-14B",
|
| 3 |
+
"candidate_slug": "flywheel-local-coder-14b",
|
| 4 |
+
"content_policy": "Model weight bodies were not read, copied, or hashed by this metadata staging command.",
|
| 5 |
+
"generated_utc": "2026-07-09T20:32:36.042999Z",
|
| 6 |
+
"model": "14B",
|
| 7 |
+
"publish_policy": "Do not publish until benchmark, endpoint, checksum, provenance, and operator approval gates pass.",
|
| 8 |
+
"release_identity": {
|
| 9 |
+
"adapter": "checkpoint-2020 (QLoRA CPT, train_loss 0.035)",
|
| 10 |
+
"artifact_kind": "gguf-qlora-cpt-merge",
|
| 11 |
+
"artifact_name": "telos-coder-14b-cpt2020-q4_k_m.gguf",
|
| 12 |
+
"base_license": "Apache-2.0",
|
| 13 |
+
"base_model": "Qwen2.5-Coder-14B-Instruct",
|
| 14 |
+
"declared_artifact_sha256": "613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be",
|
| 15 |
+
"no_artifact_reason": "",
|
| 16 |
+
"public_name": "Flywheel-Local-Coder-14B",
|
| 17 |
+
"ship_manifest": "tasks/research/gguf_ship_manifest_checkpoint2020.json",
|
| 18 |
+
"trained": true
|
| 19 |
+
},
|
| 20 |
+
"repo_id": "HarperZ9/flywheel-local-coder-14b",
|
| 21 |
+
"schema": "harness.model-repo-stage.provenance/v1",
|
| 22 |
+
"source_model_root": "E:\\local-model-run\\release\\flywheel-local-coder-14b",
|
| 23 |
+
"source_verdict": "MODEL_RELEASE_READY_STATIC",
|
| 24 |
+
"trained": true,
|
| 25 |
+
"trained_artifact_present": true,
|
| 26 |
+
"weight_file_count": 1,
|
| 27 |
+
"weight_files": [
|
| 28 |
+
{
|
| 29 |
+
"content_read": false,
|
| 30 |
+
"name": "telos-coder-14b-cpt2020-q4_k_m.gguf",
|
| 31 |
+
"size_bytes": 8988110880,
|
| 32 |
+
"suffix": ".gguf"
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"weight_total_size_bytes": 8988110880
|
| 36 |
+
}
|
release-checklist.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Flywheel-Local-Coder-14B Release Checklist
|
| 2 |
+
|
| 3 |
+
Status: blocked. The trained artifact exists; endpoint gate history and benchmark evidence do not.
|
| 4 |
+
|
| 5 |
+
Gate ids match `scripts/run_model_publish_plan.py` and `scripts/run_model_release_readiness.py`.
|
| 6 |
+
|
| 7 |
+
| Gate id | Status | Evidence |
|
| 8 |
+
| --- | --- | --- |
|
| 9 |
+
| `trained_artifact_present` | DONE | `E:\local-model-run\release\flywheel-local-coder-14b\telos-coder-14b-cpt2020-q4_k_m.gguf`, sha256 `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be`. |
|
| 10 |
+
| `root_exists` | DONE | `E:\local-model-run` and the release directory exist. |
|
| 11 |
+
| `weights_present` | DONE | GGUF weight file present at the artifact path above (8,988,110,880 bytes). |
|
| 12 |
+
| `endpoint_profiles_present` | pending | `harness.model-endpoint-profiles/v1` artifact attached to the release row (backend ollama, model `flywheel-local-coder-14b`, `http://127.0.0.1:11434`). |
|
| 13 |
+
| `endpoint_generation_ok` | pending | `harness.model-endpoint-gate/v1` artifact with generation_ok for this model. |
|
| 14 |
+
| `benchmark_evidence_present` | pending | Executed benchmark artifacts attached to the release row. None exist yet. |
|
| 15 |
+
| `release_docs_complete` | pending | All required release docs present and scored 1.0 by the readiness run. |
|
| 16 |
+
| Operator upload approval | pending, NEVER auto-approved | Explicit operator approval after all gates pass. |
|
| 17 |
+
|
| 18 |
+
Verdict: do not publish.
|
safety.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Flywheel-Local-Coder-14B Safety and Accountability Notes
|
| 2 |
+
|
| 3 |
+
Status: draft. Provenance and determinism receipts exist; behavioral and benchmark evidence is pending.
|
| 4 |
+
|
| 5 |
+
## Accountability posture
|
| 6 |
+
|
| 7 |
+
This release makes no capability claims. It states what the artifact is, how it was built, and which receipts back each statement. Anything without a receipt is labeled pending.
|
| 8 |
+
|
| 9 |
+
## Receipts that exist
|
| 10 |
+
|
| 11 |
+
- Provenance chain (`C:\dev\local-model\tasks\research\gguf_ship_manifest_checkpoint2020.json`, schema `telos.model-artifact/v1`), each layer re-derivable:
|
| 12 |
+
corpus_content_hash `68345cdc6667f20d1678ac0a9139edc170348dfdebb9ae6045cde3d204f4fe62` -> pack_shards_hash `018798dfce7d4c86f5a6ea502a383553220f2e76facfe76acbe52b1c278ae543` -> checkpoint_adapter_sha256 `4de07c6ea342d1cc200d4a6e2b28a63f6ee37f34c5c0926c35d8c7db74d38d0f` -> GGUF sha256 `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be`.
|
| 13 |
+
- Deterministic smoke: llama-completion, temp 0, seed 7, n 48; reruns byte-identical (MATCH); output sha256 `970af540244384407918aa3b0172b403c24d17800e3c514c3c19937d88c7e636`.
|
| 14 |
+
|
| 15 |
+
## Receipts required before publication
|
| 16 |
+
|
| 17 |
+
- Endpoint gate artifacts (`harness.model-endpoint-gate/v1`) with generation_ok for this model.
|
| 18 |
+
- Benchmark evidence artifacts attached to the release row. Benchmarks are pending; no benchmark result exists yet.
|
| 19 |
+
- Receipt-backed limitations and known failure modes.
|
| 20 |
+
- Refusal/friction behavior, if measured.
|
| 21 |
+
- Secret-handling boundary check on all shipped examples.
|
| 22 |
+
|
| 23 |
+
## Capability claims
|
| 24 |
+
|
| 25 |
+
None. No uplift over the base `Qwen2.5-Coder-14B-Instruct` is claimed. Any comparison against the base model must come from executed benchmark artifacts, which do not exist yet.
|
usage.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Flywheel-Local-Coder-14B Usage
|
| 2 |
+
|
| 3 |
+
Status: draft. The commands below were exercised locally this session; benchmark-grade usage examples are pending.
|
| 4 |
+
|
| 5 |
+
## Ollama
|
| 6 |
+
|
| 7 |
+
The Modelfile lives next to the artifact:
|
| 8 |
+
|
| 9 |
+
```text
|
| 10 |
+
E:\local-model-run\release\flywheel-local-coder-14b\Modelfile
|
| 11 |
+
```
|
| 12 |
+
|
| 13 |
+
Create and run:
|
| 14 |
+
|
| 15 |
+
```powershell
|
| 16 |
+
ollama create flywheel-local-coder-14b -f E:\local-model-run\release\flywheel-local-coder-14b\Modelfile
|
| 17 |
+
ollama run flywheel-local-coder-14b
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
## llama.cpp
|
| 21 |
+
|
| 22 |
+
Direct completion against the GGUF, matching the deterministic smoke configuration (temp 0, seed 7):
|
| 23 |
+
|
| 24 |
+
```powershell
|
| 25 |
+
llama-completion -m E:\local-model-run\release\flywheel-local-coder-14b\telos-coder-14b-cpt2020-q4_k_m.gguf --temp 0 --seed 7 -n 48 -p "<prompt>"
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
Reruns at temp 0, seed 7 are byte-identical (smoke verdict MATCH).
|
| 29 |
+
|
| 30 |
+
## Harness endpoint profile
|
| 31 |
+
|
| 32 |
+
The flywheel harness reaches the model through this endpoint profile:
|
| 33 |
+
|
| 34 |
+
- backend: `ollama`
|
| 35 |
+
- model: `flywheel-local-coder-14b`
|
| 36 |
+
- base URL: `http://127.0.0.1:11434`
|
| 37 |
+
|
| 38 |
+
## Required before publishing usage examples
|
| 39 |
+
|
| 40 |
+
- Endpoint gate passes or the failure mode is clearly documented.
|
| 41 |
+
- Prompt examples use the same task-set contract as benchmark runs.
|
| 42 |
+
- No examples require secrets or private files.
|