esilva commited on
Commit
13a42e5
·
verified ·
1 Parent(s): ae45729

Add the validated DirectML build to the v4b ONNX builds (v0.3.1-preview)

Browse files
NOTICE.md CHANGED
@@ -1,6 +1,6 @@
1
  # NOTICE
2
 
3
- KapiCoder-Mongo-Small-ONNX (version v4b, tag `v0.3.0-preview`) is a derivative work of `Qwen/Qwen2.5-Coder-1.5B` (revision `df3ce67c0e24480f20468b6ef2894622d69eb73b`),
4
  licensed under the Apache License, Version 2.0 (see `LICENSE`).
5
 
6
  **Modifications:** fine-tuning for MongoDB fill-in-the-middle autocomplete in the `editor-context-v1` format (see the safetensors repository `esilva/KapiCoder-Mongo-Small` for the data and the method),
@@ -13,5 +13,5 @@ The teacher used to produce part of the training labels and the training data ar
13
 
14
  # AVISO (pt-BR)
15
 
16
- KapiCoder-Mongo-Small-ONNX (versão v4b, tag `v0.3.0-preview`) é um trabalho derivado e **modificado** de `Qwen/Qwen2.5-Coder-1.5B` (revisão `df3ce67c0e24480f20468b6ef2894622d69eb73b`), licenciado sob a Apache License 2.0 (veja `LICENSE`).
17
  Modificações: ajuste fino para autocomplete FIM de MongoDB, exportação para ONNX e, quando o nome da pasta indica, quantização. Não é um produto da Alibaba Cloud nem da equipe Qwen e não tem endosso deles.
 
1
  # NOTICE
2
 
3
+ KapiCoder-Mongo-Small-ONNX (version v4b, tag `v0.3.1-preview`) is a derivative work of `Qwen/Qwen2.5-Coder-1.5B` (revision `df3ce67c0e24480f20468b6ef2894622d69eb73b`),
4
  licensed under the Apache License, Version 2.0 (see `LICENSE`).
5
 
6
  **Modifications:** fine-tuning for MongoDB fill-in-the-middle autocomplete in the `editor-context-v1` format (see the safetensors repository `esilva/KapiCoder-Mongo-Small` for the data and the method),
 
13
 
14
  # AVISO (pt-BR)
15
 
16
+ KapiCoder-Mongo-Small-ONNX (versão v4b, tag `v0.3.1-preview`) é um trabalho derivado e **modificado** de `Qwen/Qwen2.5-Coder-1.5B` (revisão `df3ce67c0e24480f20468b6ef2894622d69eb73b`), licenciado sob a Apache License 2.0 (veja `LICENSE`).
17
  Modificações: ajuste fino para autocomplete FIM de MongoDB, exportação para ONNX e, quando o nome da pasta indica, quantização. Não é um produto da Alibaba Cloud nem da equipe Qwen e não tem endosso deles.
README.md CHANGED
@@ -19,9 +19,9 @@ tags:
19
 
20
  # KapiCoder-Mongo-Small-ONNX (1.5B)
21
 
22
- > **Status: PREVIEW / experimental, public preview, not qualified.** ONNX builds of [`esilva/KapiCoder-Mongo-Small`](https://huggingface.co/esilva/KapiCoder-Mongo-Small) (version v4b, tag `v0.3.0-preview`)
23
- > for `onnxruntime-genai`, made for the *Kapibara Studio* editor. CPU builds only in this release. Read the model card of the safetensors repository first: the model, its limits and its evaluation are described there.
24
- > The previous builds stay available by tag: v4 (same contract, with a DirectML build) at [`v0.2.0-preview`](https://huggingface.co/esilva/KapiCoder-Mongo-Small-ONNX/tree/v0.2.0-preview),
25
  > v3 (`editor-context-v1`) at [`v0.1.0-preview`](https://huggingface.co/esilva/KapiCoder-Mongo-Small-ONNX/tree/v0.1.0-preview).
26
 
27
  ## What is here
@@ -32,6 +32,7 @@ cursor-in-call suite with the `editor-context-v2` prompt (300 short, 120 long pr
32
  | Folder | Build | Greedy tokens identical to bf16 | Suffix-consistent bf16 / ONNX | Field-grounded bf16 / ONNX |
33
  |---|---|---:|---|---|
34
  | `cpu-int8/` | INT8, CPU (onnxruntime-genai, `cpu` provider) | 83.1% | 94.5% / 94.5% | 93.0% / 93.0% |
 
35
 
36
  Internal evaluation on synthetic data. No difference in these metrics was statistically significant (paired McNemar); token-level differences grow on
37
  long prompts. Each folder holds `model.onnx` (with `model.onnx.data` when the weights are external), `genai_config.json` (`search.max_length` 8192),
@@ -46,6 +47,9 @@ local paths were removed). Builds were produced with `onnxruntime-genai` 0.15.2
46
  - **EOS integration requirement (GenAI 0.15.2):** EOS may finish generation without appending a token. The IDE consumes a token only when
47
  `GetSequence(0)` grows after `GenerateNextToken`; checking `IsDone()` alone after generating can discard a valid token.
48
  - **Quantised and converted builds can differ from the bf16 weights.** Measure on your own prompts before relying on one; latency depends on the host.
 
 
 
49
  - The model only suggests text and never executes anything; validate field names before running a suggestion.
50
 
51
  ## License, modification notice and attribution
@@ -58,7 +62,7 @@ local paths were removed). Builds were produced with `onnxruntime-genai` 0.15.2
58
 
59
  ## Resumo em português (pt-BR)
60
 
61
- **Status: PREVIEW / experimental, preview público, não qualificado.** Builds ONNX de CPU do `esilva/KapiCoder-Mongo-Small` (versão v4b, tag `v0.3.0-preview`) para o `onnxruntime-genai`,
62
- feitos para o editor Kapibara Studio, com o contrato `editor-context-v2`. A v4 continua na tag `v0.2.0-preview` e a v3 na `v0.1.0-preview`. Na paridade com os pesos bf16 (420 casos da
63
  suíte cursor-in-call, prompts de até 8k), a qualidade não mudou de forma significativa. Editores sem `editor-context-v2` recusam estes pacotes.
64
  Licença Apache-2.0 com aviso de modificação (derivado do Qwen2.5-Coder-1.5B, sem endosso da equipe Qwen).
 
19
 
20
  # KapiCoder-Mongo-Small-ONNX (1.5B)
21
 
22
+ > **Status: PREVIEW / experimental, public preview, not qualified.** ONNX builds of [`esilva/KapiCoder-Mongo-Small`](https://huggingface.co/esilva/KapiCoder-Mongo-Small) (version v4b, tag `v0.3.1-preview`)
23
+ > for `onnxruntime-genai`, made for the *Kapibara Studio* editor. CPU builds and a DirectML build (`dml-fp16`); the DirectML build was validated only on an AMD Radeon RX 7800 XT (16 GB) under Windows 11. Read the model card of the safetensors repository first: the model, its limits and its evaluation are described there.
24
+ > The previous builds stay available by tag: the same v4b weights with CPU builds only at [`v0.3.0-preview`](https://huggingface.co/esilva/KapiCoder-Mongo-Small-ONNX/tree/v0.3.0-preview), v4 (same contract, with a DirectML build) at [`v0.2.0-preview`](https://huggingface.co/esilva/KapiCoder-Mongo-Small-ONNX/tree/v0.2.0-preview),
25
  > v3 (`editor-context-v1`) at [`v0.1.0-preview`](https://huggingface.co/esilva/KapiCoder-Mongo-Small-ONNX/tree/v0.1.0-preview).
26
 
27
  ## What is here
 
32
  | Folder | Build | Greedy tokens identical to bf16 | Suffix-consistent bf16 / ONNX | Field-grounded bf16 / ONNX |
33
  |---|---|---:|---|---|
34
  | `cpu-int8/` | INT8, CPU (onnxruntime-genai, `cpu` provider) | 83.1% | 94.5% / 94.5% | 93.0% / 93.0% |
35
+ | `dml-fp16/` | FP16, DirectML (onnxruntime-genai, `dml` provider) | 86.0% | 94.5% / 94.5% | 93.0% / 93.0% |
36
 
37
  Internal evaluation on synthetic data. No difference in these metrics was statistically significant (paired McNemar); token-level differences grow on
38
  long prompts. Each folder holds `model.onnx` (with `model.onnx.data` when the weights are external), `genai_config.json` (`search.max_length` 8192),
 
47
  - **EOS integration requirement (GenAI 0.15.2):** EOS may finish generation without appending a token. The IDE consumes a token only when
48
  `GetSequence(0)` grows after `GenerateNextToken`; checking `IsDone()` alone after generating can discard a valid token.
49
  - **Quantised and converted builds can differ from the bf16 weights.** Measure on your own prompts before relying on one; latency depends on the host.
50
+ - **DirectML picks the GPU through Windows.** On a machine with an integrated and a discrete GPU, `device_id` did not change the adapter in our tests;
51
+ the Windows graphics preference of the host process did. Set the host process to "High performance" or the build may run on the integrated GPU.
52
+ DirectML latency was not measured for this release.
53
  - The model only suggests text and never executes anything; validate field names before running a suggestion.
54
 
55
  ## License, modification notice and attribution
 
62
 
63
  ## Resumo em português (pt-BR)
64
 
65
+ **Status: PREVIEW / experimental, preview público, não qualificado.** Builds ONNX de CPU e DirectML do `esilva/KapiCoder-Mongo-Small` (versão v4b, tag `v0.3.1-preview`) para o `onnxruntime-genai`,
66
+ feitos para o editor Kapibara Studio, com o contrato `editor-context-v2`. A mesma v4b só com CPU fica na tag `v0.3.0-preview`. A v4 continua na tag `v0.2.0-preview` e a v3 na `v0.1.0-preview`. Na paridade com os pesos bf16 (420 casos da
67
  suíte cursor-in-call, prompts de até 8k), a qualidade não mudou de forma significativa. Editores sem `editor-context-v2` recusam estes pacotes.
68
  Licença Apache-2.0 com aviso de modificação (derivado do Qwen2.5-Coder-1.5B, sem endosso da equipe Qwen).
dml-fp16/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 2024 Alibaba Cloud
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
dml-fp16/NOTICE.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ # NOTICE
2
+
3
+ KapiCoder-Mongo-Small ONNX `dml-fp16` (4.1.0-preview.1) e um trabalho derivado e **modificado** de `Qwen/Qwen2.5-Coder-1.5B` (revisao `df3ce67c0e24480f20468b6ef2894622d69eb73b`), licenciado sob
4
+ Apache License 2.0 (ver `LICENSE`).
5
+
6
+ Modificacoes: ajuste fino LoRA r=64 (fundido nos pesos) no corpus v4b (alvos destilados do KapiTeacher-Mongo-7B, derivado de Qwen/Qwen2.5-Coder-7B; consultas geradas por LLM local Qwen3-14B, Apache-2.0, validadas por execucao; cortes de gramatica; replay). Os pesos do professor nao fazem parte deste pacote para autocomplete FIM de MongoDB no contrato `editor-context-v2` (dataset `v4b`);
7
+ exportacao para ONNX e quantizacao (fp16, provider dml) com onnxruntime-genai 0.15.2.
8
+ Este pacote nao e um produto da Alibaba Cloud/Qwen. Os dados sinteticos (schemas ficticios) nao contem dados pessoais; o replay de codigo vem de
9
+ pacotes npm com licencas MIT/Apache-2.0/BSD/ISC.
dml-fp16/README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ # KapiCoder-Mongo-Small v4b ONNX DML-FP16
2
+
3
+ Autocomplete FIM de MongoDB para o Kapibara Studio (1.5B, tier T1), pacote ONNX `dml-fp16` para GPU DirectML.
4
+
5
+ - Contrato de contexto: `editor-context-v2` (QwenFimPromptBuilder + cabecalho do editor com TARGET FIELDS; pos-processamento fecha os delimitadores internos), contexto 8,192 tokens, ate 128 tokens gerados, greedy.
6
+ - Paradas: `<|fim_prefix|>`, `<|fim_suffix|>`, `<|fim_middle|>`, `<|endoftext|>`, `<|im_end|>`, `<|fim_pad|>`.
7
+ - Runtime: onnxruntime-genai >= 0.15.2 (`model.type = qwen2`, adapter Qwen da IDE).
8
+ - Base: `Qwen/Qwen2.5-Coder-1.5B` @ `df3ce67c0e24480f20468b6ef2894622d69eb73b` (Apache-2.0). Dataset `v4b`. Licenca Apache-2.0 (`LICENSE`, `NOTICE.md`).
9
+ - Integridade: `kapicoder_manifest.json` (SHA-256 de cada arquivo) e `export_manifest.json` (ferramenta, comando, tamanhos).
10
+ - Estado: **candidato nao qualificado**. Medidas de paridade/latencia do Python sao PROXY; o gate oficial vem do KapiLab/harness da IDE.
dml-fp16/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
dml-fp16/export_manifest.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema": "kapi-export-manifest-v1",
3
+ "package": "KapiCoder-Mongo-Small-v4b-ONNX-dml-fp16",
4
+ "tier": "T1",
5
+ "variant": "dml-fp16",
6
+ "generation": "v4b",
7
+ "created_utc": "2026-11-16T21:52:53Z",
8
+ "source": {
9
+ "merged_dir": "sft_v4b",
10
+ "files_sha256": {
11
+ "config.json": "9dd8637a8aaa2eb099a2fbfcc1f3a13c47055b870a850fe807a90f91470165ed",
12
+ "generation_config.json": "444ea57ebf361c659d1f5c23508319b691e181d122588ea3cdd5f68d3e618b1f",
13
+ "merges.txt": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
14
+ "model.safetensors": "6c176541e4e144f5558bcd0b3fba516baf0e80d5676243c89af821f7eb1eb148",
15
+ "tokenizer.json": "c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539",
16
+ "tokenizer_config.json": "4a917e4772d9b246ef600e1c5d7d81e3a81ae9f3f2d10d78ccb02c86e5fb184a",
17
+ "vocab.json": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
18
+ },
19
+ "combined_sha256": "b199a1e17084b9c32836c7ae76f54914182d2766664663051b7a51779fb92039",
20
+ "dtype": "bfloat16",
21
+ "base": {
22
+ "path": "Qwen2.5-Coder-1.5B",
23
+ "repo_id": "Qwen/Qwen2.5-Coder-1.5B",
24
+ "revision": "df3ce67c0e24480f20468b6ef2894622d69eb73b",
25
+ "model_sha256": "8bcb242c05f271406b3f585b7688f86e350413612ef67bca6c61700b22d05f3b",
26
+ "tokenizer_sha256_identical_to_teacher": true
27
+ },
28
+ "dataset_version": "v4b",
29
+ "training": {
30
+ "method_kind": "lora",
31
+ "corpusManifestSha256": "6f86e8ce54c703f55e12d48f8343f2f64bd76382e96705fe38b60ebb900ea311",
32
+ "corpusExamples": 205238,
33
+ "trainConfigSha256": "52618d327e688aab6b93489514c7295bf464d6f1d6596dfcb46197eb875d013f",
34
+ "trainFingerprint": "b452de73db11e82a4c6de46dd0015b56bff2eda2c1d869a2c0eedbe4c719ff5b",
35
+ "trainGitCommit": "8d9cb764110ab62d5d1a7be7e8ff6deefe60a9f6"
36
+ }
37
+ },
38
+ "build": {
39
+ "tool": "onnxruntime_genai.models.builder",
40
+ "tool_version": "0.15.2",
41
+ "precision": "fp16",
42
+ "execution_provider": "dml",
43
+ "extra_options": [],
44
+ "command": "python.exe -I -m onnxruntime_genai.models.builder -i sft_v4b -o KapiCoder-Mongo-Small-v4b-ONNX-dml-fp16 -p fp16 -e dml -c export_cache_t1_dml-fp16",
45
+ "build_seconds": 11.0
46
+ },
47
+ "total_bytes": 3107606936,
48
+ "files": [
49
+ {
50
+ "path": "added_tokens.json",
51
+ "sha256": "f0acedf99e19ec0a5b797ffbd0b94328172ccd90f7f385bbc521cda2701b03ab",
52
+ "bytes": 629
53
+ },
54
+ {
55
+ "path": "genai_config.json",
56
+ "sha256": "f2c429b10924c1dae7b9f00c5ae43cdbb15278aadc2592b633f51152e3fe8453",
57
+ "bytes": 1386
58
+ },
59
+ {
60
+ "path": "generation_config.json",
61
+ "sha256": "444ea57ebf361c659d1f5c23508319b691e181d122588ea3cdd5f68d3e618b1f",
62
+ "bytes": 117
63
+ },
64
+ {
65
+ "path": "kapibarastudio-model.json",
66
+ "sha256": "56ca7fe21dcccb16dc5f19c8810ef3394a29b455e07274b065e13d1d3f27615c",
67
+ "bytes": 2479
68
+ },
69
+ {
70
+ "path": "kapicoder_manifest.json",
71
+ "sha256": "fa29cf428b7e61dbbee2362a5c96e384ba6c1318cfde8fe7ab569ee18fdeb031",
72
+ "bytes": 2306
73
+ },
74
+ {
75
+ "path": "LICENSE",
76
+ "sha256": "832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e",
77
+ "bytes": 11343
78
+ },
79
+ {
80
+ "path": "merges.txt",
81
+ "sha256": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
82
+ "bytes": 1671839
83
+ },
84
+ {
85
+ "path": "model.onnx",
86
+ "sha256": "24f259bbc3a4b403355e732da8e9f4e90f35219d5d7a2ce3ff6231b7dcf656e1",
87
+ "bytes": 243411
88
+ },
89
+ {
90
+ "path": "model.onnx.data",
91
+ "sha256": "edff0bbb6c87a7ec1b4c81b6c3f9dbbc7a3d17b057fac5fa844e4bf42e76656a",
92
+ "bytes": 3095855104
93
+ },
94
+ {
95
+ "path": "NOTICE.md",
96
+ "sha256": "03bccebf65502526dfce420d39785764d3e6f7c0acaf14e166080c73bb6507b2",
97
+ "bytes": 911
98
+ },
99
+ {
100
+ "path": "README.md",
101
+ "sha256": "2c8f1bc3cc34b671b4bc3e0faf749fb62733a7fd038ee1e1a684cd1dd6f34ec8",
102
+ "bytes": 978
103
+ },
104
+ {
105
+ "path": "special_tokens_map.json",
106
+ "sha256": "a9b9de9d109651567e89fee2768f5a034e5b0036ce56ebfaece94d8842ed406d",
107
+ "bytes": 647
108
+ },
109
+ {
110
+ "path": "tokenizer.json",
111
+ "sha256": "c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539",
112
+ "bytes": 7031645
113
+ },
114
+ {
115
+ "path": "tokenizer_config.json",
116
+ "sha256": "4a917e4772d9b246ef600e1c5d7d81e3a81ae9f3f2d10d78ccb02c86e5fb184a",
117
+ "bytes": 7308
118
+ },
119
+ {
120
+ "path": "vocab.json",
121
+ "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
122
+ "bytes": 2776833
123
+ }
124
+ ],
125
+ "sanitized": "caminhos locais trocados pelo ultimo componente ao montar o staging; o original fica so no workspace"
126
+ }
dml-fp16/genai_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 151643,
4
+ "context_length": 32768,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "dml": {
11
+ "enable_graph_capture": "1"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 128,
18
+ "hidden_size": 1536,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "position_ids": "position_ids",
23
+ "past_key_names": "past_key_values.%d.key",
24
+ "past_value_names": "past_key_values.%d.value"
25
+ },
26
+ "outputs": {
27
+ "logits": "logits",
28
+ "present_key_names": "present.%d.key",
29
+ "present_value_names": "present.%d.value"
30
+ },
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 28,
33
+ "num_key_value_heads": 2
34
+ },
35
+ "eos_token_id": 151643,
36
+ "pad_token_id": 151643,
37
+ "type": "qwen2",
38
+ "vocab_size": 151936
39
+ },
40
+ "search": {
41
+ "diversity_penalty": 0.0,
42
+ "do_sample": false,
43
+ "early_stopping": true,
44
+ "length_penalty": 1.0,
45
+ "max_length": 8192,
46
+ "min_length": 0,
47
+ "no_repeat_ngram_size": 0,
48
+ "num_beams": 1,
49
+ "num_return_sequences": 1,
50
+ "past_present_share_buffer": true,
51
+ "repetition_penalty": 1.0,
52
+ "temperature": 1.0,
53
+ "top_k": 50,
54
+ "top_p": 1.0
55
+ }
56
+ }
dml-fp16/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.43.1"
6
+ }
dml-fp16/kapibarastudio-model.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema": "kapilab-kapi-model-v1",
3
+ "name": "KapiCoder-Mongo-Small v4b ONNX DML-FP16",
4
+ "version": "4.1.0-preview.1",
5
+ "architecture": "qwen2",
6
+ "parameters": "1.5B",
7
+ "domain": [
8
+ "mongodb",
9
+ "mongosh",
10
+ "json",
11
+ "kapibara-dsl"
12
+ ],
13
+ "capabilities": [
14
+ "autocomplete",
15
+ "fim"
16
+ ],
17
+ "hardware": [
18
+ "gpu"
19
+ ],
20
+ "contextContract": "editor-context-v2",
21
+ "recommendedContextTokens": 8192,
22
+ "recommendedCompletionTokens": 128,
23
+ "generation": {
24
+ "autocomplete": {
25
+ "maxTokens": 128,
26
+ "temperature": 0
27
+ }
28
+ },
29
+ "maximumContextTokens": 8192,
30
+ "postprocess": {
31
+ "closeInnerDelimiters": true
32
+ },
33
+ "runtime": {
34
+ "minimumGenAi": "0.15.2"
35
+ },
36
+ "stopSequences": [
37
+ "<|fim_prefix|>",
38
+ "<|fim_suffix|>",
39
+ "<|fim_middle|>",
40
+ "<|endoftext|>",
41
+ "<|im_end|>",
42
+ "<|fim_pad|>"
43
+ ],
44
+ "tier": "T1",
45
+ "variant": "dml-fp16",
46
+ "license": "Apache-2.0",
47
+ "modification": "Modelo derivado e MODIFICADO de Qwen/Qwen2.5-Coder-1.5B (ajuste fino de dominio MongoDB no corpus v4b: cortes com o cursor dentro das chamadas, destilacao do KapiTeacher-Mongo-7B, consultas geradas por LLM local (Qwen3-14B, Apache-2.0) validadas por execucao, exemplos longos de 8k e replay de codigo; exportado e quantizado para ONNX). Nao e um produto da Alibaba Cloud/Qwen.",
48
+ "base": {
49
+ "repo_id": "Qwen/Qwen2.5-Coder-1.5B",
50
+ "revision": "df3ce67c0e24480f20468b6ef2894622d69eb73b",
51
+ "license": "Apache-2.0"
52
+ },
53
+ "datasetVersion": "v4b",
54
+ "training": {
55
+ "run": "sft_v4b",
56
+ "method": "SFT ajuste fino LoRA r=64 (fundido nos pesos) FIM editor-context-v2 (TARGET FIELDS), janela de 8k, corpus v4b (corpus v4 cursor-in-call + 25% de fim_ctx/completion da fonte llm-qwen3-14b; none+irrelevant em 45% dos cortes com cabecalho; alvos destilados do KapiTeacher-Mongo-7B v3c; longos de 8k; replay)",
57
+ "mergedWeightsSha256": "6c176541e4e144f5558bcd0b3fba516baf0e80d5676243c89af821f7eb1eb148",
58
+ "method_kind": "lora",
59
+ "corpusManifestSha256": "6f86e8ce54c703f55e12d48f8343f2f64bd76382e96705fe38b60ebb900ea311",
60
+ "corpusExamples": 205238,
61
+ "trainConfigSha256": "52618d327e688aab6b93489514c7295bf464d6f1d6596dfcb46197eb875d013f",
62
+ "trainFingerprint": "b452de73db11e82a4c6de46dd0015b56bff2eda2c1d869a2c0eedbe4c719ff5b",
63
+ "trainGitCommit": "8d9cb764110ab62d5d1a7be7e8ff6deefe60a9f6"
64
+ },
65
+ "manifest": "kapicoder_manifest.json",
66
+ "status": "candidate-unqualified (medidas proxy do Python; o gate oficial e do KapiLab)"
67
+ }
dml-fp16/kapicoder_manifest.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema": "kapilab-kapicoder-manifest-v1",
3
+ "package": "KapiCoder-Mongo-Small-v4b-ONNX-dml-fp16",
4
+ "version": "4.1.0-preview.1",
5
+ "created_utc": "2026-11-16T21:52:51Z",
6
+ "files": [
7
+ {
8
+ "path": "added_tokens.json",
9
+ "sha256": "f0acedf99e19ec0a5b797ffbd0b94328172ccd90f7f385bbc521cda2701b03ab",
10
+ "bytes": 629
11
+ },
12
+ {
13
+ "path": "genai_config.json",
14
+ "sha256": "f2c429b10924c1dae7b9f00c5ae43cdbb15278aadc2592b633f51152e3fe8453",
15
+ "bytes": 1386
16
+ },
17
+ {
18
+ "path": "generation_config.json",
19
+ "sha256": "444ea57ebf361c659d1f5c23508319b691e181d122588ea3cdd5f68d3e618b1f",
20
+ "bytes": 117
21
+ },
22
+ {
23
+ "path": "kapibarastudio-model.json",
24
+ "sha256": "56ca7fe21dcccb16dc5f19c8810ef3394a29b455e07274b065e13d1d3f27615c",
25
+ "bytes": 2479
26
+ },
27
+ {
28
+ "path": "LICENSE",
29
+ "sha256": "832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e",
30
+ "bytes": 11343
31
+ },
32
+ {
33
+ "path": "merges.txt",
34
+ "sha256": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
35
+ "bytes": 1671839
36
+ },
37
+ {
38
+ "path": "model.onnx",
39
+ "sha256": "24f259bbc3a4b403355e732da8e9f4e90f35219d5d7a2ce3ff6231b7dcf656e1",
40
+ "bytes": 243411
41
+ },
42
+ {
43
+ "path": "model.onnx.data",
44
+ "sha256": "edff0bbb6c87a7ec1b4c81b6c3f9dbbc7a3d17b057fac5fa844e4bf42e76656a",
45
+ "bytes": 3095855104
46
+ },
47
+ {
48
+ "path": "NOTICE.md",
49
+ "sha256": "03bccebf65502526dfce420d39785764d3e6f7c0acaf14e166080c73bb6507b2",
50
+ "bytes": 911
51
+ },
52
+ {
53
+ "path": "README.md",
54
+ "sha256": "2c8f1bc3cc34b671b4bc3e0faf749fb62733a7fd038ee1e1a684cd1dd6f34ec8",
55
+ "bytes": 978
56
+ },
57
+ {
58
+ "path": "special_tokens_map.json",
59
+ "sha256": "a9b9de9d109651567e89fee2768f5a034e5b0036ce56ebfaece94d8842ed406d",
60
+ "bytes": 647
61
+ },
62
+ {
63
+ "path": "tokenizer.json",
64
+ "sha256": "c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539",
65
+ "bytes": 7031645
66
+ },
67
+ {
68
+ "path": "tokenizer_config.json",
69
+ "sha256": "4a917e4772d9b246ef600e1c5d7d81e3a81ae9f3f2d10d78ccb02c86e5fb184a",
70
+ "bytes": 7308
71
+ },
72
+ {
73
+ "path": "vocab.json",
74
+ "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
75
+ "bytes": 2776833
76
+ }
77
+ ]
78
+ }
dml-fp16/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
dml-fp16/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f259bbc3a4b403355e732da8e9f4e90f35219d5d7a2ce3ff6231b7dcf656e1
3
+ size 243411
dml-fp16/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edff0bbb6c87a7ec1b4c81b6c3f9dbbc7a3d17b057fac5fa844e4bf42e76656a
3
+ size 3095855104
dml-fp16/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
dml-fp16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
dml-fp16/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
dml-fp16/vocab.json ADDED
The diff for this file is too large to render. See raw diff