Instructions to use Lucasgitguy-co/wiki-model-tiny-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 Lucasgitguy-co/wiki-model-tiny-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 Lucasgitguy-co/wiki-model-tiny-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Lucasgitguy-co/wiki-model-tiny-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lucasgitguy-co/wiki-model-tiny-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Lucasgitguy-co/wiki-model-tiny-GGUF:F16
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 Lucasgitguy-co/wiki-model-tiny-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf Lucasgitguy-co/wiki-model-tiny-GGUF:F16
Use Docker
docker model run hf.co/Lucasgitguy-co/wiki-model-tiny-GGUF:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use Lucasgitguy-co/wiki-model-tiny-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lucasgitguy-co/wiki-model-tiny-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lucasgitguy-co/wiki-model-tiny-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Lucasgitguy-co/wiki-model-tiny-GGUF:F16
- Ollama
How to use Lucasgitguy-co/wiki-model-tiny-GGUF with Ollama:
ollama run hf.co/Lucasgitguy-co/wiki-model-tiny-GGUF:F16
- Unsloth Desktop
- Docker Model Runner
How to use Lucasgitguy-co/wiki-model-tiny-GGUF with Docker Model Runner:
docker model run hf.co/Lucasgitguy-co/wiki-model-tiny-GGUF:F16
- Lemonade
How to use Lucasgitguy-co/wiki-model-tiny-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lucasgitguy-co/wiki-model-tiny-GGUF:F16
Run and chat with the model
lemonade run user.wiki-model-tiny-GGUF-F16
List all available models
lemonade list
- Atomic Chat
Add GGUF conversion (tested with llama.cpp build 12359)
Browse files- .gitattributes +2 -0
- LICENSE +176 -0
- README.md +51 -0
- convert_tiny.py +65 -0
- wiki-model-tiny-F16.gguf +3 -0
- wiki-model-tiny-Q8_0.gguf +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip 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
|
|
|
|
|
|
|
|
|
| 33 |
*.zip 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 |
+
wiki-model-tiny-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
wiki-model-tiny-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Lucasgitguy-co/wiki-model-tiny
|
| 4 |
+
base_model_relation: quantized
|
| 5 |
+
library_name: gguf
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
language: en
|
| 8 |
+
tags:
|
| 9 |
+
- gguf
|
| 10 |
+
- llama.cpp
|
| 11 |
+
- wikipedia
|
| 12 |
+
- facts
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# wiki-model-tiny GGUF
|
| 16 |
+
|
| 17 |
+
GGUF files of [Lucasgitguy-co/wiki-model-tiny](https://huggingface.co/Lucasgitguy-co/wiki-model-tiny), a 12.5M-parameter model trained from scratch. It runs in llama.cpp as a normal `llama` model.
|
| 18 |
+
|
| 19 |
+
| File | Type | Size (GB) |
|
| 20 |
+
| --- | --- | ---: |
|
| 21 |
+
| `wiki-model-tiny-F16.gguf` | F16, same output as the original | 0.025 |
|
| 22 |
+
| `wiki-model-tiny-Q8_0.gguf` | Q8_0 | 0.014 |
|
| 23 |
+
|
| 24 |
+
There are no K-quants: the model width (320) isn't a multiple of 256.
|
| 25 |
+
|
| 26 |
+
## Use
|
| 27 |
+
|
| 28 |
+
The prompt tags are `<fact> topic </fact>`, `<q> question </q>`, `<fix> claim </fix>`, and an optional `<ctx> text </ctx> ` in front. The context window is 384 tokens.
|
| 29 |
+
|
| 30 |
+
```bash
|
| 31 |
+
hf download Lucasgitguy-co/wiki-model-tiny-GGUF wiki-model-tiny-F16.gguf --local-dir .
|
| 32 |
+
llama-completion -m wiki-model-tiny-F16.gguf -no-cnv --temp 0 -n 80 -c 384 \
|
| 33 |
+
-p "<ctx> Mount Everest is Earth's highest mountain, in the Himalayas. </ctx> <q> Where is Mount Everest? </q>"
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
The Python package's `--grounded` BM25 index isn't included, so supply the context yourself. Without context this model mostly makes things up.
|
| 37 |
+
|
| 38 |
+
## How these were made and tested
|
| 39 |
+
|
| 40 |
+
- The original is plain PyTorch, so `convert_tiny.py` writes the GGUF directly with gguf-py:
|
| 41 |
+
- The fused `qkv` and `gate_up` weights are split.
|
| 42 |
+
- RoPE is kept as is, because the model already uses llama.cpp's interleaved layout.
|
| 43 |
+
- The byte-level BPE tokenizer is stored as `gpt2` with the `gpt-2` pre-tokenizer.
|
| 44 |
+
- Tested 2026-11-16 with llama.cpp 1.0.0 (build 12359):
|
| 45 |
+
- Token ids match the original tokenizer on all three prompt formats.
|
| 46 |
+
- Greedy output (F32 and F16) is identical to the PyTorch model on 4 prompts, up to the end-of-answer token.
|
| 47 |
+
- Q8_0 was spot-checked on one prompt.
|
| 48 |
+
|
| 49 |
+
## Licence
|
| 50 |
+
|
| 51 |
+
Apache-2.0, the same as the source model. Wikipedia-derived training data is CC BY-SA 4.0.
|
convert_tiny.py
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Write wiki-model-tiny (TinyGPT) as a llama-arch GGUF directly with gguf-py.
|
| 2 |
+
TinyGPT already uses interleaved (GPT-J style) RoPE pairs, which is llama.cpp's LLAMA rope, so q/k are NOT permuted.
|
| 3 |
+
usage: python convert_tiny.py MODEL_DIR OUT.gguf [f32|f16]"""
|
| 4 |
+
import json, sys
|
| 5 |
+
import numpy as np
|
| 6 |
+
from safetensors.numpy import load_file
|
| 7 |
+
sys.path.insert(0, sys.argv[4] if len(sys.argv) > 4 else "/Users/lucasvandeweerd/.cache/spot-snake/llama.cpp/gguf-py")
|
| 8 |
+
import gguf
|
| 9 |
+
|
| 10 |
+
mdir, out = sys.argv[1], sys.argv[2]
|
| 11 |
+
ft = sys.argv[3] if len(sys.argv) > 3 else "f16"
|
| 12 |
+
c = json.load(open(f"{mdir}/config.json"))
|
| 13 |
+
sd = load_file(f"{mdir}/model.safetensors")
|
| 14 |
+
tj = json.load(open(f"{mdir}/tokenizer.json"))
|
| 15 |
+
D, H, L, F = c["dim"], c["heads"], c["layers"], c["hidden"]
|
| 16 |
+
|
| 17 |
+
w = gguf.GGUFWriter(out, "llama")
|
| 18 |
+
w.add_name("wiki-model-tiny")
|
| 19 |
+
w.add_context_length(c["ctx"]); w.add_embedding_length(D); w.add_block_count(L)
|
| 20 |
+
w.add_feed_forward_length(F); w.add_head_count(H); w.add_head_count_kv(H)
|
| 21 |
+
w.add_layer_norm_rms_eps(1e-5); w.add_rope_freq_base(c["rope_base"]); w.add_rope_dimension_count(D // H)
|
| 22 |
+
w.add_vocab_size(c["vocab"])
|
| 23 |
+
w.add_file_type(gguf.LlamaFileType.MOSTLY_F16 if ft == "f16" else gguf.LlamaFileType.ALL_F32)
|
| 24 |
+
|
| 25 |
+
# tokenizer: byte-level BPE with the GPT-2 regex == llama.cpp "gpt2" model + "gpt-2" pre-tokenizer
|
| 26 |
+
vocab = tj["model"]["vocab"]
|
| 27 |
+
added = {a["id"]: a for a in tj["added_tokens"]}
|
| 28 |
+
tokens = [None] * c["vocab"]
|
| 29 |
+
for t, i in vocab.items(): tokens[i] = t
|
| 30 |
+
for i, a in added.items(): tokens[i] = a["content"]
|
| 31 |
+
assert all(t is not None for t in tokens), "vocab has holes"
|
| 32 |
+
types = []
|
| 33 |
+
for i in range(len(tokens)):
|
| 34 |
+
if i in added:
|
| 35 |
+
types.append(gguf.TokenType.CONTROL if added[i]["content"] in ("<pad>", "<eos>") else gguf.TokenType.USER_DEFINED)
|
| 36 |
+
else:
|
| 37 |
+
types.append(gguf.TokenType.NORMAL)
|
| 38 |
+
merges = [m if isinstance(m, str) else " ".join(m) for m in tj["model"]["merges"]]
|
| 39 |
+
eos = tj["model"]["vocab"].get("<eos>", next(i for i, a in added.items() if a["content"] == "<eos>"))
|
| 40 |
+
pad = next(i for i, a in added.items() if a["content"] == "<pad>")
|
| 41 |
+
w.add_tokenizer_model("gpt2"); w.add_tokenizer_pre("gpt-2")
|
| 42 |
+
w.add_token_list(tokens); w.add_token_types(types); w.add_token_merges(merges)
|
| 43 |
+
w.add_bos_token_id(eos); w.add_eos_token_id(eos); w.add_pad_token_id(pad)
|
| 44 |
+
w.add_add_bos_token(False); w.add_add_eos_token(False)
|
| 45 |
+
|
| 46 |
+
def put(name, a, norm=False):
|
| 47 |
+
a = np.ascontiguousarray(a, dtype=np.float32 if (norm or ft == "f32") else np.float16)
|
| 48 |
+
w.add_tensor(name, a)
|
| 49 |
+
|
| 50 |
+
put("token_embd.weight", sd["emb.weight"])
|
| 51 |
+
for i in range(L):
|
| 52 |
+
p = f"blocks.{i}."
|
| 53 |
+
q, k, v = np.split(sd[p + "qkv.weight"], 3, axis=0)
|
| 54 |
+
g, u = np.split(sd[p + "gate_up.weight"], 2, axis=0) # chunk(2): gate first, then up
|
| 55 |
+
put(f"blk.{i}.attn_norm.weight", sd[p + "n1.w"], norm=True)
|
| 56 |
+
put(f"blk.{i}.attn_q.weight", q); put(f"blk.{i}.attn_k.weight", k); put(f"blk.{i}.attn_v.weight", v)
|
| 57 |
+
put(f"blk.{i}.attn_output.weight", sd[p + "o.weight"])
|
| 58 |
+
put(f"blk.{i}.ffn_norm.weight", sd[p + "n2.w"], norm=True)
|
| 59 |
+
put(f"blk.{i}.ffn_gate.weight", g); put(f"blk.{i}.ffn_up.weight", u)
|
| 60 |
+
put(f"blk.{i}.ffn_down.weight", sd[p + "down.weight"])
|
| 61 |
+
put("output_norm.weight", sd["norm.w"], norm=True)
|
| 62 |
+
used = {"emb.weight", "norm.w"} | {f"blocks.{i}.{n}" for i in range(L) for n in ("qkv.weight", "gate_up.weight", "n1.w", "n2.w", "o.weight", "down.weight")}
|
| 63 |
+
assert used == set(sd), set(sd) ^ used
|
| 64 |
+
w.write_header_to_file(); w.write_kv_data_to_file(); w.write_tensors_to_file(); w.close()
|
| 65 |
+
print("wrote", out)
|
wiki-model-tiny-F16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82a7c992ba51b8024e573a59aabcfed79c70e6788b38ffeaf35c54f9a87f0531
|
| 3 |
+
size 25359296
|
wiki-model-tiny-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd19dc5eb1096767e8a5fe8c698f431d2742f679ca48f94c5ec2982795abeb61
|
| 3 |
+
size 13608928
|