Instructions to use ngquocvinh/Spark-X2.5-1.7B-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 ngquocvinh/Spark-X2.5-1.7B-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 ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ngquocvinh/Spark-X2.5-1.7B-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 ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ngquocvinh/Spark-X2.5-1.7B-GGUF: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 ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf ngquocvinh/Spark-X2.5-1.7B-GGUF: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 ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ngquocvinh/Spark-X2.5-1.7B-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": "ngquocvinh/Spark-X2.5-1.7B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
- Ollama
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with Ollama:
ollama run hf.co/ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ngquocvinh/Spark-X2.5-1.7B-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:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with Docker Model Runner:
docker model run hf.co/ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
- Lemonade
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Spark-X2.5-1.7B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ngquocvinh/Spark-X2.5-1.7B-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 ngquocvinh/Spark-X2.5-1.7B-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://127.0.0.1:8080/v1 hermes config set model.default ngquocvinh/Spark-X2.5-1.7B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ngquocvinh/Spark-X2.5-1.7B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ngquocvinh/Spark-X2.5-1.7B-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://127.0.0.1:8080/v1 \ --custom-model-id "ngquocvinh/Spark-X2.5-1.7B-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 Spark-X2.5 1.7B GGUF quantizations
Browse files- .gitattributes +12 -0
- LICENSE +202 -0
- README.md +93 -0
- SHA256SUMS.txt +9 -0
- Spark-X2.5-1.7B-IQ1_M.gguf +3 -0
- Spark-X2.5-1.7B-IQ2_XS.gguf +3 -0
- Spark-X2.5-1.7B-Q1_0.gguf +3 -0
- Spark-X2.5-1.7B-Q2_K.gguf +3 -0
- Spark-X2.5-1.7B-Q3_K_M.gguf +3 -0
- Spark-X2.5-1.7B-Q4_K_M.gguf +3 -0
- Spark-X2.5-1.7B-Q5_K_M.gguf +3 -0
- Spark-X2.5-1.7B-Q6_K.gguf +3 -0
- Spark-X2.5-1.7B-Q8_0.gguf +3 -0
- chat_template.jinja +110 -0
- reproducibility/README.md +42 -0
- reproducibility/benchmark_gpu0.sh +51 -0
- reproducibility/gpu_smoke_test_ladder.sh +50 -0
- reproducibility/perplexity_ladder.sh +51 -0
- reproducibility/quantize_ladder.sh +49 -0
- reproducibility/smoke_test_ladder.sh +49 -0
- reproducibility/spark25_1.7b_combined.imatrix.gguf +3 -0
- reproducibility/spark25_1.7b_vn_code_agent.imatrix.gguf +3 -0
- reproducibility/spark25_1.7b_wiki.imatrix.gguf +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,15 @@ 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 |
+
Spark-X2.5-1.7B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Spark-X2.5-1.7B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Spark-X2.5-1.7B-Q1_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Spark-X2.5-1.7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Spark-X2.5-1.7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Spark-X2.5-1.7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
Spark-X2.5-1.7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
Spark-X2.5-1.7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
Spark-X2.5-1.7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
reproducibility/spark25_1.7b_combined.imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
reproducibility/spark25_1.7b_vn_code_agent.imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
reproducibility/spark25_1.7b_wiki.imatrix.gguf 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 XHToken
|
| 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.
|
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: XHToken/Spark-X2.5-1.7B
|
| 4 |
+
library_name: llama.cpp
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- gguf
|
| 8 |
+
- llama.cpp
|
| 9 |
+
- spark2_5
|
| 10 |
+
- quantized
|
| 11 |
+
- text-generation
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Spark-X2.5-1.7B GGUF
|
| 15 |
+
|
| 16 |
+
Unofficial community GGUF quantizations of
|
| 17 |
+
[XHToken/Spark-X2.5-1.7B](https://huggingface.co/XHToken/Spark-X2.5-1.7B).
|
| 18 |
+
This repository contains nine quantized files for local inference. No
|
| 19 |
+
training or fine-tuning was performed.
|
| 20 |
+
|
| 21 |
+
## Files
|
| 22 |
+
|
| 23 |
+
| Quantization | Size | GPU0 generation | Recommendation |
|
| 24 |
+
|---|---:|---:|---|
|
| 25 |
+
| Q8_0 | 1.70 GiB | 175.54 tok/s | High quality |
|
| 26 |
+
| Q6_K | 1.31 GiB | 199.07 tok/s | High quality |
|
| 27 |
+
| Q5_K_M | 1.17 GiB | 223.04 tok/s | Daily use |
|
| 28 |
+
| Q4_K_M | 1.03 GiB | 241.87 tok/s | Recommended default |
|
| 29 |
+
| Q3_K_M | 0.87 GiB | 203.60 tok/s | Lower memory |
|
| 30 |
+
| Q2_K | 0.74 GiB | 231.70 tok/s | Aggressive |
|
| 31 |
+
| IQ2_XS | 0.61 GiB | 245.03 tok/s | Experimental |
|
| 32 |
+
| IQ1_M | 0.54 GiB | 252.02 tok/s | Experimental |
|
| 33 |
+
| Q1_0 | 0.40 GiB | 336.65 tok/s | Experimental / legacy |
|
| 34 |
+
|
| 35 |
+
The speed figures are single-stream `llama-bench` readings on one NVIDIA
|
| 36 |
+
A10M, with 256 prompt tokens, 64 generated tokens, 64 CPU threads, 99 GPU
|
| 37 |
+
layers, and three repetitions. They are not quality scores or universal
|
| 38 |
+
hardware benchmarks.
|
| 39 |
+
|
| 40 |
+
Q1/Q2 and the IQ variants can lose instruction following, reasoning, and
|
| 41 |
+
tool-call reliability. Validate the chosen file on the workload that matters
|
| 42 |
+
to you.
|
| 43 |
+
|
| 44 |
+
## Quick start
|
| 45 |
+
|
| 46 |
+
Use the Spark-compatible build of
|
| 47 |
+
[XHToken/llama.cpp](https://github.com/XHToken/llama.cpp):
|
| 48 |
+
|
| 49 |
+
```bash
|
| 50 |
+
./build/bin/llama-cli \
|
| 51 |
+
-m Spark-X2.5-1.7B-Q4_K_M.gguf \
|
| 52 |
+
-p "Explain GGUF quantization in one paragraph." \
|
| 53 |
+
-c 4096 \
|
| 54 |
+
--single-turn
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
The tokenizer and chat template metadata are embedded in each GGUF. The
|
| 58 |
+
native context limit is advertised upstream as up to 1M tokens, but that
|
| 59 |
+
requires substantial KV-cache memory and was not validated here.
|
| 60 |
+
|
| 61 |
+
## Build and validation
|
| 62 |
+
|
| 63 |
+
The files were converted and quantized with XHToken's Spark-enabled
|
| 64 |
+
llama.cpp at commit `4a3635c32fc9f044c2bde9ebeabf50c7e1ec5991`.
|
| 65 |
+
|
| 66 |
+
- BF16 conversion: PASS
|
| 67 |
+
- CPU smoke test: 9/9 PASS
|
| 68 |
+
- GPU0 smoke test: 9/9 PASS
|
| 69 |
+
- GPU0 benchmark: 10 configurations, three repetitions each
|
| 70 |
+
- Perplexity comparison: BF16 plus nine quantizations
|
| 71 |
+
|
| 72 |
+
The quantized outputs were generated directly from the official
|
| 73 |
+
`Spark-X2.5-1.7B.gguf` conversion. Q8_0 uses no importance matrix; all other
|
| 74 |
+
files use the model-specific combined matrix included under
|
| 75 |
+
`reproducibility/`.
|
| 76 |
+
|
| 77 |
+
Portable scripts, manifests, calibration matrices, and validation summaries
|
| 78 |
+
are in [`reproducibility/`](reproducibility/). The original BF16 source and
|
| 79 |
+
the llama.cpp build are not duplicated in this repo; set `SOURCE` and
|
| 80 |
+
`LLAMA_CPP` when reproducing locally.
|
| 81 |
+
|
| 82 |
+
## License and attribution
|
| 83 |
+
|
| 84 |
+
The upstream model is released under Apache License 2.0. Preserve the
|
| 85 |
+
upstream attribution and license when redistributing these derivative files.
|
| 86 |
+
This is an unofficial quantization and is not endorsed by XHToken/SparkLLM.
|
| 87 |
+
|
| 88 |
+
Checksums are available in [`SHA256SUMS.txt`](SHA256SUMS.txt).
|
| 89 |
+
|
| 90 |
+
If this quantization saved you time, VRAM, or compute cost, consider leaving
|
| 91 |
+
a small tip. It helps fund future quantizations.
|
| 92 |
+
|
| 93 |
+
☕ [Support me on Ko-fi](https://ko-fi.com/ngquocvinh)
|
SHA256SUMS.txt
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
09ca0c14edf63de5f903569082b21151413bbded716218fc4b8a6e2932c743de Spark-X2.5-1.7B-IQ1_M.gguf
|
| 2 |
+
e74f48b63553292b39e84af754d5f0b46eec794e17a8ec98f5df0aaf10b020c3 Spark-X2.5-1.7B-IQ2_XS.gguf
|
| 3 |
+
ac3774c91e8cd21134a25f6fe528b81eb134f5da9b97f5f947e75f0de73a6e07 Spark-X2.5-1.7B-Q1_0.gguf
|
| 4 |
+
7da639353647e73533422484e21b074e5ac0eb6a7de6827bf716105a5b1aee59 Spark-X2.5-1.7B-Q2_K.gguf
|
| 5 |
+
18a86766ed0c2ed91ac265b2871641b638ce40e8084132df483e315e1ef86060 Spark-X2.5-1.7B-Q3_K_M.gguf
|
| 6 |
+
bddd0ac6f86f67280dc6a9c79eb3bb739bb3d63b050dffc908fcc3d6728b2d0d Spark-X2.5-1.7B-Q4_K_M.gguf
|
| 7 |
+
7d25d301cc02b5c9603f35ddd9d80e74ea9926ae3312b52eb509e7c89f862a66 Spark-X2.5-1.7B-Q5_K_M.gguf
|
| 8 |
+
551a8627287e2f99a257fe9f27d44e7553088c0e4e07da7ef0a1c13b60f7db70 Spark-X2.5-1.7B-Q6_K.gguf
|
| 9 |
+
c81e5c973366cbd12472d66992e629352a9d0c304633b9f1c917297a05bb30ae Spark-X2.5-1.7B-Q8_0.gguf
|
Spark-X2.5-1.7B-IQ1_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09ca0c14edf63de5f903569082b21151413bbded716218fc4b8a6e2932c743de
|
| 3 |
+
size 574820096
|
Spark-X2.5-1.7B-IQ2_XS.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e74f48b63553292b39e84af754d5f0b46eec794e17a8ec98f5df0aaf10b020c3
|
| 3 |
+
size 656157952
|
Spark-X2.5-1.7B-Q1_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3774c91e8cd21134a25f6fe528b81eb134f5da9b97f5f947e75f0de73a6e07
|
| 3 |
+
size 428425984
|
Spark-X2.5-1.7B-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da639353647e73533422484e21b074e5ac0eb6a7de6827bf716105a5b1aee59
|
| 3 |
+
size 790237952
|
Spark-X2.5-1.7B-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a86766ed0c2ed91ac265b2871641b638ce40e8084132df483e315e1ef86060
|
| 3 |
+
size 937380096
|
Spark-X2.5-1.7B-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bddd0ac6f86f67280dc6a9c79eb3bb739bb3d63b050dffc908fcc3d6728b2d0d
|
| 3 |
+
size 1107457792
|
Spark-X2.5-1.7B-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d25d301cc02b5c9603f35ddd9d80e74ea9926ae3312b52eb509e7c89f862a66
|
| 3 |
+
size 1252480768
|
Spark-X2.5-1.7B-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:551a8627287e2f99a257fe9f27d44e7553088c0e4e07da7ef0a1c13b60f7db70
|
| 3 |
+
size 1406567680
|
Spark-X2.5-1.7B-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c81e5c973366cbd12472d66992e629352a9d0c304633b9f1c917297a05bb30ae
|
| 3 |
+
size 1820112352
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#- 0826版本 -#}
|
| 2 |
+
{%- if not messages %}
|
| 3 |
+
{{- raise_exception('No messages provided.') }}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- set enable_thinking = enable_thinking | default(true) %}
|
| 6 |
+
|
| 7 |
+
{#- Render a string or a list of text blocks. -#}
|
| 8 |
+
{%- macro render_content(content, context_name) %}
|
| 9 |
+
{%- if content is string %}
|
| 10 |
+
{{- content }}
|
| 11 |
+
{%- elif content is none or content is undefined %}
|
| 12 |
+
{{- '' }}
|
| 13 |
+
{%- elif content is iterable and content is not mapping %}
|
| 14 |
+
{%- for block in content %}
|
| 15 |
+
{%- if block.type == 'text' %}
|
| 16 |
+
{{- block.text }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- raise_exception('Unsupported ' ~ context_name ~ ' content block type: ' ~ (block.type | string)) }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endfor %}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{{- raise_exception(context_name ~ ' content must be a string or a list of text blocks') }}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endmacro %}
|
| 25 |
+
|
| 26 |
+
{#- Default system prompt -#}
|
| 27 |
+
{%- set default_system = "you are a helpful assistant." %}
|
| 28 |
+
|
| 29 |
+
{#- The first message-level system is placed in the initial system block. -#}
|
| 30 |
+
{%- set ns = namespace(initial_system='') %}
|
| 31 |
+
{%- if messages[0].role == "system" %}
|
| 32 |
+
{%- set ns.initial_system = render_content(messages[0].content, 'system') %}
|
| 33 |
+
{%- endif %}
|
| 34 |
+
|
| 35 |
+
{#- System block -#}
|
| 36 |
+
{{- '<|start▁of▁sentence|><|System|>' + '\n' + default_system }}
|
| 37 |
+
{%- if tools %}
|
| 38 |
+
{{- '## Tools' + '\n' + 'You have access to the following functions:' + '\n' + '<tools>' }}
|
| 39 |
+
{%- for tool in tools %}
|
| 40 |
+
{{- '\n' + tool.function | tojson}}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- '\n' + '</tools>' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- if ns.initial_system %}
|
| 45 |
+
{{- '\n\n' + ns.initial_system }}
|
| 46 |
+
{%- endif %}
|
| 47 |
+
{{- '<|end▁of▁sentence|>'}}
|
| 48 |
+
|
| 49 |
+
{#- Conversation turns -#}
|
| 50 |
+
{%- for message in messages %}
|
| 51 |
+
{%- if message.role == "system" %}
|
| 52 |
+
{#- The first system message was consumed by the initial block. -#}
|
| 53 |
+
{%- if not loop.first %}
|
| 54 |
+
{{- '<|start▁of▁sentence|><|System|>\n' + render_content(message.content, 'system') + '<|end▁of▁sentence|>' }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.role == "user" %}
|
| 57 |
+
{{- '<|start▁of▁sentence|><|User|>' + render_content(message.content, 'user') + '<|end▁of▁sentence|>' }}
|
| 58 |
+
{%- elif message.role == "assistant" %}
|
| 59 |
+
{%- set assistant_content = render_content(message.content, 'assistant') %}
|
| 60 |
+
{%- if message.reasoning_content is defined and message.reasoning_content %}
|
| 61 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 62 |
+
{%- else %}
|
| 63 |
+
{%- set reasoning_content = '' %}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{{- '<|start▁of▁sentence|><|Bot|>'}}
|
| 66 |
+
{%- if reasoning_content %}
|
| 67 |
+
{{- '<think>' + reasoning_content + '</think>'}}
|
| 68 |
+
{%- else %}
|
| 69 |
+
{{- '</think>' }}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{%- if assistant_content %}
|
| 72 |
+
{{- assistant_content }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- if message.tool_calls is defined and message.tool_calls is not none %}
|
| 75 |
+
{%- for tool_call in message.tool_calls %}
|
| 76 |
+
{%- if tool_call.function.arguments is not mapping %}
|
| 77 |
+
{{- raise_exception('tool_call.function.arguments must be a dictionary; normalize JSON strings before apply_chat_template') }}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- set args = tool_call.function.arguments %}
|
| 80 |
+
{{- '<tool_call>' + tool_call.function.name }}
|
| 81 |
+
{%- for k, v in args.items() %}
|
| 82 |
+
{{- '<arg_key>' ~ k ~ '</arg_key><arg_value>' ~ (v if v is string else v | tojson) ~ '</arg_value>' }}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{{- '</tool_call>' }}
|
| 85 |
+
{%- endfor %}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{{- '<|end▁of▁sentence|>' }}
|
| 88 |
+
{%- elif message.role == "tool" %}
|
| 89 |
+
{%- if loop.previtem is undefined or loop.previtem.role != "tool" %}
|
| 90 |
+
{{- '<|start▁of▁sentence|><|Tool|>' }}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{{- '<tool_response>' ~ message.content ~ '</tool_response>' }}
|
| 93 |
+
{%- if loop.nextitem is undefined or loop.nextitem.role != "tool" %}
|
| 94 |
+
{{- '<|end▁of▁sentence|>' }}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- else %}
|
| 97 |
+
{{- raise_exception('Unsupported message role: ' ~ message.role) }}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- endfor %}
|
| 100 |
+
|
| 101 |
+
{#- Generation prompt -#}
|
| 102 |
+
{%- if add_generation_prompt %}
|
| 103 |
+
{{- '<|start▁of▁sentence|><|Bot|>' }}
|
| 104 |
+
{%- if enable_thinking is defined and enable_thinking %}
|
| 105 |
+
{{- '<think>' }}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{%- if enable_thinking is defined and not enable_thinking %}
|
| 108 |
+
{{- '</think>' }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endif %}
|
reproducibility/README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Spark-X2.5-1.7B reproducibility
|
| 2 |
+
|
| 3 |
+
This directory contains the reproducible conversion, calibration,
|
| 4 |
+
quantization, smoke-test, and benchmark scripts for Spark-X2.5-1.7B.
|
| 5 |
+
|
| 6 |
+
## Source and conversion
|
| 7 |
+
|
| 8 |
+
- Source: `../source-hf-1.7b/`
|
| 9 |
+
- Converted source: `../source-official-bf16-1.7b/Spark-X2.5-1.7B.gguf`
|
| 10 |
+
- Converter: `../tools-llama.cpp-spark/convert_hf_to_gguf.py`
|
| 11 |
+
- llama.cpp commit: `4a3635c32fc9f044c2bde9ebeabf50c7e1ec5991`
|
| 12 |
+
- Architecture: `Spark2_5ForCausalLM` / `spark2_5`
|
| 13 |
+
|
| 14 |
+
The converter dry-run and full conversion both completed successfully. The
|
| 15 |
+
source uses a 1,048,576-token native position limit and a 512-token sliding
|
| 16 |
+
window; the serving profile intentionally caps active context at 65,536.
|
| 17 |
+
|
| 18 |
+
## Calibration and quantization
|
| 19 |
+
|
| 20 |
+
The imatrix is model-specific and combines:
|
| 21 |
+
|
| 22 |
+
- 5 chunks from `../calibration/spark25_vn_code_agent.txt`
|
| 23 |
+
- 96 chunks from `../calibration/wikitext-2-raw/wiki.test.raw`
|
| 24 |
+
- 101 chunks total in `spark25_1.7b_combined.imatrix.gguf`
|
| 25 |
+
|
| 26 |
+
Run the ladder with:
|
| 27 |
+
|
| 28 |
+
```sh
|
| 29 |
+
bash quantize_ladder.sh
|
| 30 |
+
bash smoke_test_ladder.sh
|
| 31 |
+
bash perplexity_ladder.sh
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
GPU0 smoke and benchmark require the GPU0 model services to be stopped first:
|
| 35 |
+
|
| 36 |
+
```sh
|
| 37 |
+
bash gpu_smoke_test_ladder.sh
|
| 38 |
+
bash benchmark_gpu0.sh
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
The scripts use the local XHToken Spark build and do not reuse the 4B
|
| 42 |
+
imatrix.
|
reproducibility/benchmark_gpu0.sh
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -euo pipefail
|
| 3 |
+
|
| 4 |
+
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
| 5 |
+
PACKAGE_ROOT="$(cd -- "$SCRIPT_DIR/.." && pwd)"
|
| 6 |
+
WORKSPACE_ROOT="${WORKSPACE_ROOT:-$PACKAGE_ROOT/..}"
|
| 7 |
+
LLAMA_CPP="${LLAMA_CPP:-$WORKSPACE_ROOT/tools-llama.cpp-spark}"
|
| 8 |
+
BENCH="${BENCH:-$LLAMA_CPP/build/bin/llama-bench}"
|
| 9 |
+
SOURCE="${SOURCE:-$WORKSPACE_ROOT/source-official-bf16-1.7b/Spark-X2.5-1.7B.gguf}"
|
| 10 |
+
MODEL_DIR="${MODEL_DIR:-$PACKAGE_ROOT}"
|
| 11 |
+
THREADS="${THREADS:-64}"
|
| 12 |
+
REPETITIONS="${REPETITIONS:-3}"
|
| 13 |
+
OUTDIR="${OUTDIR:-$WORKSPACE_ROOT/reports/spark-1.7b/benchmark-gpu0}"
|
| 14 |
+
RAW="$OUTDIR/llama-bench-raw"
|
| 15 |
+
|
| 16 |
+
mkdir -p "$RAW"
|
| 17 |
+
|
| 18 |
+
models=(
|
| 19 |
+
"BF16|$SOURCE"
|
| 20 |
+
"Q8_0|$MODEL_DIR/Spark-X2.5-1.7B-Q8_0.gguf"
|
| 21 |
+
"Q6_K|$MODEL_DIR/Spark-X2.5-1.7B-Q6_K.gguf"
|
| 22 |
+
"Q5_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q5_K_M.gguf"
|
| 23 |
+
"Q4_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q4_K_M.gguf"
|
| 24 |
+
"Q3_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q3_K_M.gguf"
|
| 25 |
+
"Q2_K|$MODEL_DIR/Spark-X2.5-1.7B-Q2_K.gguf"
|
| 26 |
+
"IQ2_XS|$MODEL_DIR/Spark-X2.5-1.7B-IQ2_XS.gguf"
|
| 27 |
+
"IQ1_M|$MODEL_DIR/Spark-X2.5-1.7B-IQ1_M.gguf"
|
| 28 |
+
"Q1_0|$MODEL_DIR/Spark-X2.5-1.7B-Q1_0.gguf"
|
| 29 |
+
)
|
| 30 |
+
|
| 31 |
+
for item in "${models[@]}"; do
|
| 32 |
+
label="${item%%|*}"
|
| 33 |
+
model="${item#*|}"
|
| 34 |
+
echo "benchmarking GPU0 $label"
|
| 35 |
+
CUDA_VISIBLE_DEVICES=0 "$BENCH" \
|
| 36 |
+
-m "$model" \
|
| 37 |
+
-p 256 \
|
| 38 |
+
-n 64 \
|
| 39 |
+
-r "$REPETITIONS" \
|
| 40 |
+
-b 512 \
|
| 41 |
+
-ub 512 \
|
| 42 |
+
-t "$THREADS" \
|
| 43 |
+
-ngl 99 \
|
| 44 |
+
--device CUDA0 \
|
| 45 |
+
-o csv \
|
| 46 |
+
>"$RAW/$label.csv" \
|
| 47 |
+
2>"$RAW/$label.stderr"
|
| 48 |
+
done
|
| 49 |
+
|
| 50 |
+
LLAMA_BENCH_REPETITIONS="$REPETITIONS" python3 "${SUMMARIZER:-$WORKSPACE_ROOT/reproducibility/summarize_bench.py}" "$RAW" "$OUTDIR/speed-summary.tsv"
|
| 51 |
+
echo "benchmark artifacts: $OUTDIR"
|
reproducibility/gpu_smoke_test_ladder.sh
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -u
|
| 3 |
+
|
| 4 |
+
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
| 5 |
+
PACKAGE_ROOT="$(cd -- "$SCRIPT_DIR/.." && pwd)"
|
| 6 |
+
LLAMA_CPP="${LLAMA_CPP:-$PACKAGE_ROOT/../tools-llama.cpp-spark}"
|
| 7 |
+
CLI="${CLI:-$LLAMA_CPP/build/bin/llama-cli}"
|
| 8 |
+
MODEL_DIR="${MODEL_DIR:-$PACKAGE_ROOT}"
|
| 9 |
+
LOGDIR="${LOGDIR:-$PACKAGE_ROOT/../reports/spark-1.7b/smoke-tests-gpu0}"
|
| 10 |
+
SUMMARY="${SUMMARY:-$PACKAGE_ROOT/../reports/spark-1.7b/smoke-test-gpu0.tsv}"
|
| 11 |
+
|
| 12 |
+
mkdir -p "$LOGDIR"
|
| 13 |
+
printf 'model\tstatus\tlog\n' > "$SUMMARY"
|
| 14 |
+
|
| 15 |
+
models=(
|
| 16 |
+
Spark-X2.5-1.7B-Q8_0.gguf
|
| 17 |
+
Spark-X2.5-1.7B-Q6_K.gguf
|
| 18 |
+
Spark-X2.5-1.7B-Q5_K_M.gguf
|
| 19 |
+
Spark-X2.5-1.7B-Q4_K_M.gguf
|
| 20 |
+
Spark-X2.5-1.7B-Q3_K_M.gguf
|
| 21 |
+
Spark-X2.5-1.7B-Q2_K.gguf
|
| 22 |
+
Spark-X2.5-1.7B-IQ2_XS.gguf
|
| 23 |
+
Spark-X2.5-1.7B-IQ1_M.gguf
|
| 24 |
+
Spark-X2.5-1.7B-Q1_0.gguf
|
| 25 |
+
)
|
| 26 |
+
|
| 27 |
+
for model in "${models[@]}"; do
|
| 28 |
+
log="$LOGDIR/${model%.gguf}.log"
|
| 29 |
+
echo "testing GPU0 $model"
|
| 30 |
+
if CUDA_VISIBLE_DEVICES=0 timeout 180 "$CLI" \
|
| 31 |
+
-m "$MODEL_DIR/$model" \
|
| 32 |
+
-p 'Trả lời ngắn bằng tiếng Việt: GGUF là gì?' \
|
| 33 |
+
-n 48 \
|
| 34 |
+
-c 2048 \
|
| 35 |
+
-dev CUDA0 \
|
| 36 |
+
-ngl 99 \
|
| 37 |
+
--single-turn \
|
| 38 |
+
--simple-io \
|
| 39 |
+
--no-display-prompt \
|
| 40 |
+
--temp 0.2 \
|
| 41 |
+
--top-p 0.95 \
|
| 42 |
+
--seed 42 \
|
| 43 |
+
--log-verbosity 1 >"$log" 2>&1; then
|
| 44 |
+
status=PASS
|
| 45 |
+
else
|
| 46 |
+
status=FAIL
|
| 47 |
+
fi
|
| 48 |
+
printf '%s\t%s\t%s\n' "$model" "$status" "$log" >> "$SUMMARY"
|
| 49 |
+
echo "$status $model"
|
| 50 |
+
done
|
reproducibility/perplexity_ladder.sh
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -euo pipefail
|
| 3 |
+
|
| 4 |
+
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
| 5 |
+
PACKAGE_ROOT="$(cd -- "$SCRIPT_DIR/.." && pwd)"
|
| 6 |
+
WORKSPACE_ROOT="${WORKSPACE_ROOT:-$PACKAGE_ROOT/..}"
|
| 7 |
+
LLAMA_CPP="${LLAMA_CPP:-$WORKSPACE_ROOT/tools-llama.cpp-spark}"
|
| 8 |
+
PPL="${PPL:-$LLAMA_CPP/build/bin/llama-perplexity}"
|
| 9 |
+
SOURCE="${SOURCE:-$WORKSPACE_ROOT/source-official-bf16-1.7b/Spark-X2.5-1.7B.gguf}"
|
| 10 |
+
MODEL_DIR="${MODEL_DIR:-$PACKAGE_ROOT}"
|
| 11 |
+
CALIBRATION_FILE="${CALIBRATION_FILE:-$WORKSPACE_ROOT/calibration/wikitext-2-raw/wiki.test.raw}"
|
| 12 |
+
THREADS="${THREADS:-64}"
|
| 13 |
+
OUTDIR="${OUTDIR:-$WORKSPACE_ROOT/reports/spark-1.7b/perplexity}"
|
| 14 |
+
LOGDIR="$OUTDIR/logs"
|
| 15 |
+
|
| 16 |
+
mkdir -p "$LOGDIR"
|
| 17 |
+
|
| 18 |
+
models=(
|
| 19 |
+
"Spark-X2.5-1.7B|$SOURCE"
|
| 20 |
+
"Spark-X2.5-1.7B-Q8_0|$MODEL_DIR/Spark-X2.5-1.7B-Q8_0.gguf"
|
| 21 |
+
"Spark-X2.5-1.7B-Q6_K|$MODEL_DIR/Spark-X2.5-1.7B-Q6_K.gguf"
|
| 22 |
+
"Spark-X2.5-1.7B-Q5_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q5_K_M.gguf"
|
| 23 |
+
"Spark-X2.5-1.7B-Q4_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q4_K_M.gguf"
|
| 24 |
+
"Spark-X2.5-1.7B-Q3_K_M|$MODEL_DIR/Spark-X2.5-1.7B-Q3_K_M.gguf"
|
| 25 |
+
"Spark-X2.5-1.7B-Q2_K|$MODEL_DIR/Spark-X2.5-1.7B-Q2_K.gguf"
|
| 26 |
+
"Spark-X2.5-1.7B-IQ2_XS|$MODEL_DIR/Spark-X2.5-1.7B-IQ2_XS.gguf"
|
| 27 |
+
"Spark-X2.5-1.7B-IQ1_M|$MODEL_DIR/Spark-X2.5-1.7B-IQ1_M.gguf"
|
| 28 |
+
"Spark-X2.5-1.7B-Q1_0|$MODEL_DIR/Spark-X2.5-1.7B-Q1_0.gguf"
|
| 29 |
+
)
|
| 30 |
+
|
| 31 |
+
for item in "${models[@]}"; do
|
| 32 |
+
label="${item%%|*}"
|
| 33 |
+
model="${item#*|}"
|
| 34 |
+
echo "perplexity $label"
|
| 35 |
+
timeout 900 "$PPL" \
|
| 36 |
+
-m "$model" \
|
| 37 |
+
-f "$CALIBRATION_FILE" \
|
| 38 |
+
-c 512 \
|
| 39 |
+
-b 512 \
|
| 40 |
+
--chunks 4 \
|
| 41 |
+
-t "$THREADS" \
|
| 42 |
+
-tb "$THREADS" \
|
| 43 |
+
-ngl 0 \
|
| 44 |
+
--device none \
|
| 45 |
+
--no-warmup \
|
| 46 |
+
--log-verbosity 1 \
|
| 47 |
+
>"$LOGDIR/$label.log" 2>&1 || true
|
| 48 |
+
done
|
| 49 |
+
|
| 50 |
+
python3 "${SUMMARIZER:-$WORKSPACE_ROOT/reproducibility/summarize_ppl.py}" "$LOGDIR" "$OUTDIR/perplexity-summary.tsv"
|
| 51 |
+
echo "perplexity artifacts: $OUTDIR"
|
reproducibility/quantize_ladder.sh
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -euo pipefail
|
| 3 |
+
|
| 4 |
+
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
| 5 |
+
PACKAGE_ROOT="$(cd -- "$SCRIPT_DIR/.." && pwd)"
|
| 6 |
+
WORKSPACE_ROOT="${WORKSPACE_ROOT:-$PACKAGE_ROOT}"
|
| 7 |
+
LLAMA_CPP="${LLAMA_CPP:-$WORKSPACE_ROOT/tools-llama.cpp-spark}"
|
| 8 |
+
QUANTIZER="${QUANTIZER:-$LLAMA_CPP/build/bin/llama-quantize}"
|
| 9 |
+
SOURCE="${SOURCE:-$WORKSPACE_ROOT/source-official-bf16-1.7b/Spark-X2.5-1.7B.gguf}"
|
| 10 |
+
IMATRIX="${IMATRIX:-$SCRIPT_DIR/spark25_1.7b_combined.imatrix.gguf}"
|
| 11 |
+
OUTDIR="${OUTDIR:-$PACKAGE_ROOT}"
|
| 12 |
+
LOGDIR="${LOGDIR:-$WORKSPACE_ROOT/reports/spark-1.7b/quantize-logs}"
|
| 13 |
+
THREADS="${THREADS:-64}"
|
| 14 |
+
|
| 15 |
+
[[ -s "$SOURCE" ]] || { echo "Missing SOURCE: $SOURCE" >&2; exit 1; }
|
| 16 |
+
[[ -x "$QUANTIZER" ]] || { echo "Missing QUANTIZER: $QUANTIZER" >&2; exit 1; }
|
| 17 |
+
[[ -s "$IMATRIX" ]] || { echo "Missing IMATRIX: $IMATRIX" >&2; exit 1; }
|
| 18 |
+
|
| 19 |
+
mkdir -p "$OUTDIR" "$LOGDIR"
|
| 20 |
+
|
| 21 |
+
run_quant() {
|
| 22 |
+
local type="$1"
|
| 23 |
+
local suffix="$2"
|
| 24 |
+
local output="$OUTDIR/Spark-X2.5-1.7B-${suffix}.gguf"
|
| 25 |
+
local log="$LOGDIR/${suffix}.log"
|
| 26 |
+
|
| 27 |
+
if [[ -s "$output" ]]; then
|
| 28 |
+
echo "skip $suffix (already exists)"
|
| 29 |
+
return 0
|
| 30 |
+
fi
|
| 31 |
+
|
| 32 |
+
echo "start $suffix"
|
| 33 |
+
if [[ "$type" == "Q8_0" ]]; then
|
| 34 |
+
"$QUANTIZER" "$SOURCE" "$output" "$type" "$THREADS" >"$log" 2>&1
|
| 35 |
+
else
|
| 36 |
+
"$QUANTIZER" --imatrix "$IMATRIX" "$SOURCE" "$output" "$type" "$THREADS" >"$log" 2>&1
|
| 37 |
+
fi
|
| 38 |
+
echo "done $suffix"
|
| 39 |
+
}
|
| 40 |
+
|
| 41 |
+
run_quant Q8_0 Q8_0
|
| 42 |
+
run_quant Q6_K Q6_K
|
| 43 |
+
run_quant Q5_K_M Q5_K_M
|
| 44 |
+
run_quant Q4_K_M Q4_K_M
|
| 45 |
+
run_quant Q3_K_M Q3_K_M
|
| 46 |
+
run_quant Q2_K Q2_K
|
| 47 |
+
run_quant IQ2_XS IQ2_XS
|
| 48 |
+
run_quant IQ1_M IQ1_M
|
| 49 |
+
run_quant Q1_0 Q1_0
|
reproducibility/smoke_test_ladder.sh
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -u
|
| 3 |
+
|
| 4 |
+
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
| 5 |
+
PACKAGE_ROOT="$(cd -- "$SCRIPT_DIR/.." && pwd)"
|
| 6 |
+
LLAMA_CPP="${LLAMA_CPP:-$PACKAGE_ROOT/../tools-llama.cpp-spark}"
|
| 7 |
+
CLI="${CLI:-$LLAMA_CPP/build/bin/llama-cli}"
|
| 8 |
+
MODEL_DIR="${MODEL_DIR:-$PACKAGE_ROOT}"
|
| 9 |
+
LOGDIR="${LOGDIR:-$PACKAGE_ROOT/../reports/spark-1.7b/smoke-tests-cpu}"
|
| 10 |
+
SUMMARY="${SUMMARY:-$PACKAGE_ROOT/../reports/spark-1.7b/smoke-test-cpu.tsv}"
|
| 11 |
+
|
| 12 |
+
mkdir -p "$LOGDIR"
|
| 13 |
+
printf 'model\tstatus\tlog\n' > "$SUMMARY"
|
| 14 |
+
|
| 15 |
+
models=(
|
| 16 |
+
Spark-X2.5-1.7B-Q8_0.gguf
|
| 17 |
+
Spark-X2.5-1.7B-Q6_K.gguf
|
| 18 |
+
Spark-X2.5-1.7B-Q5_K_M.gguf
|
| 19 |
+
Spark-X2.5-1.7B-Q4_K_M.gguf
|
| 20 |
+
Spark-X2.5-1.7B-Q3_K_M.gguf
|
| 21 |
+
Spark-X2.5-1.7B-Q2_K.gguf
|
| 22 |
+
Spark-X2.5-1.7B-IQ2_XS.gguf
|
| 23 |
+
Spark-X2.5-1.7B-IQ1_M.gguf
|
| 24 |
+
Spark-X2.5-1.7B-Q1_0.gguf
|
| 25 |
+
)
|
| 26 |
+
|
| 27 |
+
for model in "${models[@]}"; do
|
| 28 |
+
log="$LOGDIR/${model%.gguf}.log"
|
| 29 |
+
echo "testing $model"
|
| 30 |
+
if timeout 180 "$CLI" \
|
| 31 |
+
-m "$MODEL_DIR/$model" \
|
| 32 |
+
-p 'Trả lời ngắn bằng tiếng Việt: GGUF là gì?' \
|
| 33 |
+
-n 48 \
|
| 34 |
+
-c 2048 \
|
| 35 |
+
-dev none \
|
| 36 |
+
--single-turn \
|
| 37 |
+
--simple-io \
|
| 38 |
+
--no-display-prompt \
|
| 39 |
+
--temp 0.2 \
|
| 40 |
+
--top-p 0.95 \
|
| 41 |
+
--seed 42 \
|
| 42 |
+
--log-verbosity 1 >"$log" 2>&1; then
|
| 43 |
+
status=PASS
|
| 44 |
+
else
|
| 45 |
+
status=FAIL
|
| 46 |
+
fi
|
| 47 |
+
printf '%s\t%s\t%s\n' "$model" "$status" "$log" >> "$SUMMARY"
|
| 48 |
+
echo "$status $model"
|
| 49 |
+
done
|
reproducibility/spark25_1.7b_combined.imatrix.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59825b29e1f0f956f903b74483635dad888b92a7539666adb280414a0a97d4f6
|
| 3 |
+
size 1918688
|
reproducibility/spark25_1.7b_vn_code_agent.imatrix.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0714c70a5e8646afd87a83cc62255aed90568c75a674cc5c9a5f691dd39480a8
|
| 3 |
+
size 1918624
|
reproducibility/spark25_1.7b_wiki.imatrix.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c861c45a059447a8a94b1d74e7557c675cc9d2daa8b68c4c88c5f26fd70ae89a
|
| 3 |
+
size 1918624
|