juyoung-trl commited on
Commit
8a1ff6a
·
verified ·
1 Parent(s): bf32b56

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ base-banner.png filter=lfs diff=lfs merge=lfs -text
.release_manifest.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "variant": "base",
3
+ "src": "/mnt/vast/trillion/juyoung/release/src/base_hf",
4
+ "tokenizer_dir": "/mnt/vast/trillion/tokenizers/glm_151k",
5
+ "context_length": 131072
6
+ }
LICENSE ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding any notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ Copyright 2026 Trillion Labs
179
+
180
+ Licensed under the Apache License, Version 2.0 (the "License");
181
+ you may not use this file except in compliance with the License.
182
+ You may obtain a copy of the License at
183
+
184
+ http://www.apache.org/licenses/LICENSE-2.0
185
+
186
+ Unless required by applicable law or agreed to in writing, software
187
+ distributed under the License is distributed on an "AS IS" BASIS,
188
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189
+ See the License for the specific language governing permissions and
190
+ limitations under the License.
README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - ko
6
+ library_name: transformers
7
+ tags:
8
+ - moe
9
+ - mixture-of-experts
10
+ - gravity
11
+ - trillion-labs
12
+ - pretrained
13
+ - base
14
+ pipeline_tag: text-generation
15
+ base_model:
16
+ - trillionlabs/Gravity-16B-A3B-Base
17
+ ---
18
+
19
+ <p align="center">
20
+ <img src="base-banner.png" alt="Gravity-30B-A5B-Base" width="100%">
21
+ </p>
22
+
23
+ # Gravity-30B-A5B-Base
24
+
25
+ **Gravity-30B-A5B-Base** is a pretrained sparse Mixture-of-Experts (MoE) language model by [Trillion Labs](https://trillionlabs.co) and the [Lunit](https://www.lunit.io) Consortium. It features 29.56B total parameters with 5.34B active parameters per token and a native 128K context window.
26
+
27
+ The model is a **depth-upscaled** continuation of [Gravity-16B-A3B-Base](https://huggingface.co/trillionlabs/Gravity-16B-A3B-Base): the 28-layer 16B model was expanded to 52 layers by block expansion (LLaMA-Pro style), then continually pretrained on a STEM-, code- and Korean-heavy mixture, followed by long-context extension to 131,072 tokens.
28
+
29
+ It ships as a stock `DeepseekV3ForCausalLM` checkpoint: no `trust_remote_code`, no custom modeling files. Any stack that serves DeepSeek-V3 (transformers, vLLM, SGLang) loads it as-is.
30
+
31
+ ## Model Summary
32
+
33
+ | Property | Value |
34
+ |---|---|
35
+ | **Total Parameters** | 29.56B |
36
+ | **Active Parameters** | 5.34B |
37
+ | **Architecture** | DeepSeek-V3 (MLA + sparse MoE), `model_type: deepseek_v3` |
38
+ | **Number of Layers** | 52 (2 dense + 50 MoE) |
39
+ | **Hidden Size** | 2048 |
40
+ | **Attention Heads** | 16 |
41
+ | **KV Heads** | 16 |
42
+ | **Routed Experts** | 64 |
43
+ | **Shared Experts** | 1 |
44
+ | **Experts per Token** | 8 |
45
+ | **MoE Intermediate Size** | 1408 |
46
+ | **Context Length** | 131,072 tokens |
47
+ | **Vocabulary Size** | 151,552 |
48
+ | **Precision** | bf16 |
49
+ | **License** | Apache 2.0 |
50
+
51
+ ## Architecture
52
+
53
+ Gravity-30B-A5B-Base uses the DeepSeek-V3 architecture ([DeepSeek-AI et al., 2024](https://arxiv.org/abs/2412.19437)), the same family as [Gravity-16B-A3B-Base](https://huggingface.co/trillionlabs/Gravity-16B-A3B-Base) and [Moonlight](https://huggingface.co/moonshotai/Moonlight-16B-A3B). Key features:
54
+
55
+ - **Multi-head Latent Attention (MLA)**: low-rank key-value compression (`kv_lora_rank=512`, `qk_nope_head_dim=128`, `qk_rope_head_dim=64`, `v_head_dim=128`) for a compact KV cache.
56
+ - **Mixture-of-Experts**: 64 routed experts with top-8 selection plus 1 shared expert. The first two layers use a dense MLP (`first_k_dense_replace=2`); all subsequent layers are MoE.
57
+ - **Sigmoid Routing with Bias Correction**: sigmoid scoring with auxiliary-loss-free load balancing via `e_score_correction_bias` (`topk_method=noaux_tc`, `routed_scaling_factor=2.446`).
58
+ - **Interleaved RoPE**: rotary embeddings with `rope_theta=1,000,000`, no scaling.
59
+
60
+ ### Comparison with Gravity-16B-A3B-Base
61
+
62
+ | Parameter | Gravity-30B-A5B-Base | Gravity-16B-A3B-Base |
63
+ |---|---|---|
64
+ | **Layers** | 52 | 28 |
65
+ | **Dense Layers** | 2 | 1 |
66
+ | **Total / Active Params** | 29.56B / 5.34B | 16.24B / 3.16B |
67
+ | **Context Length** | 131,072 | 32,768 |
68
+ | **HF Architecture** | `DeepseekV3ForCausalLM` (native) | `GravityMoEForCausalLM` (remote code) |
69
+ | **Tokenizer** | GLM-4.5 (151,552) | GLM-4.5 (151,552) |
70
+
71
+ ### Tokenizer
72
+
73
+ The tokenizer is initialized from [GLM-4.5](https://huggingface.co/zai-org/GLM-4.5) (vocabulary size 151,552). Internal evaluations across multilingual corpora found it more efficient in fertility and compression ratio than alternatives, especially for mixed English-Korean text. For the base model, `eos_token` is `<|endoftext|>`.
74
+
75
+ ## Training
76
+
77
+ 1. **Depth Upscaling** — Initialized from Gravity-16B-A3B-Base by duplicating transformer blocks (28 → 52 layers), then warmed up at 4K context.
78
+ 2. **Continued Pretraining / Annealing** — 32K context on a high-quality mixture emphasizing STEM, code, mathematics, medical literature and Korean web/text corpora.
79
+ 3. **Long-Context Extension** — 128K context training on a long-document mixture (`rope_theta=1e6`, no RoPE scaling).
80
+
81
+ ## Quickstart
82
+
83
+ ### Installation
84
+
85
+ ```bash
86
+ pip install "transformers>=4.57" torch
87
+ ```
88
+
89
+ ### Using Transformers
90
+
91
+ ```python
92
+ from transformers import AutoModelForCausalLM, AutoTokenizer
93
+ import torch
94
+
95
+ model_name = "trillionlabs/Gravity-30B-A5B-Base"
96
+
97
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
98
+ model = AutoModelForCausalLM.from_pretrained(
99
+ model_name,
100
+ dtype=torch.bfloat16,
101
+ device_map="auto",
102
+ )
103
+
104
+ input_ids = tokenizer("The theory of relativity states that", return_tensors="pt").input_ids.to(model.device)
105
+ output = model.generate(input_ids, max_new_tokens=128, do_sample=True, temperature=0.7)
106
+ print(tokenizer.decode(output[0], skip_special_tokens=True))
107
+ ```
108
+
109
+ ## Deployment
110
+
111
+ The checkpoint is a standard DeepSeek-V3 layout, so vLLM and SGLang serve it without plugins or `--trust-remote-code`.
112
+
113
+ ### vLLM
114
+
115
+ ```bash
116
+ vllm serve trillionlabs/Gravity-30B-A5B-Base --tensor-parallel-size 4 --max-model-len 131072
117
+ ```
118
+
119
+ ### SGLang
120
+
121
+ ```bash
122
+ python3 -m sglang.launch_server \
123
+ --model-path trillionlabs/Gravity-30B-A5B-Base \
124
+ --tp 4 --context-length 131072 \
125
+ --host 0.0.0.0 --port 30000
126
+ ```
127
+
128
+ ## Limitations
129
+
130
+ - This is a base pretrained model without instruction tuning or safety alignment. It may generate factually incorrect, biased, or harmful content.
131
+ - Performance may degrade on languages not well-represented in the training data.
132
+
133
+ ## Acknowledgements
134
+
135
+ This model was developed as part of a collaborative research initiative led by **Lunit** and **Trillion Labs**, with a focus on advancing foundation models for science and healthcare.
136
+
137
+ - **Lunit** — Project lead and medical AI research
138
+ - **Trillion Labs** — Model architecture, pretraining, and infrastructure
139
+ - **Aigen Science** — Biomedical AI and drug discovery research
140
+ - **SK Biopharmaceuticals** — AI-driven drug development and digital healthcare advisory
141
+ - **Kakao Healthcare** — Medical data standardization and platform support
142
+
143
+ We also thank the following participating institutions for their contributions: KAIST (Yoonjae Choi, Taekyun Kim, Jong Chul Ye, Hyunwoo Kim, Seunghoon Hong), Seoul National University (Yousung Jung), Rebellions, Standigm, NHIS Ilsan Hospital, Yongin Severance Hospital, Gangdong Kyung Hee University Hospital, Kyung Hee University Medical Center, Korea University, Konyang University Hospital, Ewha Womans University Seoul Hospital, Keimyung University Dongsan Medical Center, Pusan National University Yangsan Hospital, and D-Circle.
144
+
145
+ This work was supported by the **AI Specialized Foundation Model Project** (인공지능 특화 파운데이션 모델 프로젝트), funded by the **Ministry of Science and ICT** (과학기술정보통신부, MSIT) and managed by the **National IT Industry Promotion Agency** (NIPA, 정보통신산업진흥원).
146
+
147
+ ## License
148
+
149
+ This model is released under the [Apache 2.0 License](LICENSE).
150
+
151
+ ## Citation
152
+
153
+ ```bibtex
154
+ @misc{gravity-30b-base-2026,
155
+ title={Gravity-30B-A5B-Base},
156
+ author={Trillion Labs},
157
+ year={2026},
158
+ url={https://huggingface.co/trillionlabs/Gravity-30B-A5B-Base}
159
+ }
160
+ ```
161
+
162
+ ## Contact
163
+
164
+ - Website: [trillionlabs.co](https://trillionlabs.co)
165
+ - Website: [lunit.io](https://www.lunit.io)
base-banner.png ADDED

Git LFS Details

  • SHA256: 54bed4e916551cf578515092927be7761a0147789acde98bbe17d484d85dab20
  • Pointer size: 131 Bytes
  • Size of remote file: 203 kB
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "model_type": "deepseek_v3",
6
+ "vocab_size": 151552,
7
+ "hidden_size": 2048,
8
+ "intermediate_size": 8192,
9
+ "moe_intermediate_size": 1408,
10
+ "num_hidden_layers": 52,
11
+ "num_attention_heads": 16,
12
+ "num_key_value_heads": 16,
13
+ "q_lora_rank": null,
14
+ "kv_lora_rank": 512,
15
+ "qk_rope_head_dim": 64,
16
+ "qk_nope_head_dim": 128,
17
+ "v_head_dim": 128,
18
+ "n_routed_experts": 64,
19
+ "n_shared_experts": 1,
20
+ "num_experts_per_tok": 8,
21
+ "first_k_dense_replace": 2,
22
+ "routed_scaling_factor": 2.446,
23
+ "norm_topk_prob": true,
24
+ "scoring_func": "sigmoid",
25
+ "topk_method": "noaux_tc",
26
+ "n_group": 1,
27
+ "topk_group": 1,
28
+ "hidden_act": "silu",
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_theta": 1000000.0,
31
+ "tie_word_embeddings": false,
32
+ "moe_layer_freq": 1,
33
+ "max_position_embeddings": 131072,
34
+ "rope_scaling": null,
35
+ "rope_interleave": true,
36
+ "attention_bias": false,
37
+ "attention_dropout": 0.0,
38
+ "initializer_range": 0.02,
39
+ "use_cache": true,
40
+ "eos_token_id": 151329,
41
+ "pad_token_id": 151341,
42
+ "torch_dtype": "bfloat16",
43
+ "dtype": "bfloat16",
44
+ "transformers_version": "4.57.1"
45
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": 151329,
3
+ "pad_token_id": 151341,
4
+ "transformers_version": "4.57.1"
5
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccd0085f955ed17689144e10162232c41fad7b99d3a36bf2f4b71abdeb3436c
3
+ size 4996613400
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68fec2ce58c3544d92216fca456e5c69338a4ffa1b54d2bfff154f1e513517c
3
+ size 4996086848
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40539aa796c79418fa427c038b47d4b053c6613d83254d2c6034698eeaccd4d2
3
+ size 4995048888
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa280c9c397c935cbbc55ef5efcf53df0456b420178962523bec6e573c81dd5
3
+ size 4996087728
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb0f05a0a10eefe173c911dbab6e73350c25877c6a4236c7be586d731693de6
3
+ size 4996087728
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd402ccfad9ab1b8a620882f8a2e348643ff6208088082fd28a4b27e4ca77ff3
3
+ size 4995048912
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e980c582d709d8628bbb2f6ff053d0a43eb8ece866ae155f1ea6feffbc5014
3
+ size 4996087728
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df48c7455e89666364fdad429cc4fa9498fa1d048db753ad5a4ac0a19520f58d
3
+ size 4996087728
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0f697d0302f1030290418de6bf8293aab81114c30998f02c2f53053163891b
3
+ size 4995048920
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:193db93f89e00354d22deb5122441cb58ac964dd20e730626c5c6dec655ec264
3
+ size 4996087728
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d1bb267915486b6fe8981f11539985a459968e6255a67d2aabfc4007c40096
3
+ size 4996087728
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5c645cc4a9150f895919957210f9247c6214e4dc2c38d8fa9ff2aaf34c9dd0
3
+ size 4164530152
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>",
17
+ "<|begin_of_audio|>",
18
+ "<|end_of_audio|>",
19
+ "<|begin_of_transcription|>",
20
+ "<|end_of_transcription|>",
21
+ "<|code_prefix|>",
22
+ "<|code_middle|>",
23
+ "<|code_suffix|>",
24
+ "/nothink"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bab92a832d50b9d28c453fb77debc0f598c4d6ab4b1eb69181d555a5c97ecb
3
+ size 19970701
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|begin_of_audio|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|end_of_audio|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "151346": {
140
+ "content": "<|end_of_transcription|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "151347": {
148
+ "content": "<|code_prefix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "151348": {
156
+ "content": "<|code_middle|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "151349": {
164
+ "content": "<|code_suffix|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "151350": {
172
+ "content": "<think>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "</think>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151352": {
188
+ "content": "<tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151353": {
196
+ "content": "</tool_call>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151354": {
204
+ "content": "<tool_response>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "151355": {
212
+ "content": "</tool_response>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "151356": {
220
+ "content": "<arg_key>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "151357": {
228
+ "content": "</arg_key>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "151358": {
236
+ "content": "<arg_value>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "151359": {
244
+ "content": "</arg_value>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "151360": {
252
+ "content": "/nothink",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "151361": {
260
+ "content": "<|begin_of_box|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "151362": {
268
+ "content": "<|end_of_box|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "151363": {
276
+ "content": "<|image|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "151364": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ }
291
+ },
292
+ "additional_special_tokens": [
293
+ "<|endoftext|>",
294
+ "[MASK]",
295
+ "[gMASK]",
296
+ "[sMASK]",
297
+ "<sop>",
298
+ "<eop>",
299
+ "<|system|>",
300
+ "<|user|>",
301
+ "<|assistant|>",
302
+ "<|observation|>",
303
+ "<|begin_of_image|>",
304
+ "<|end_of_image|>",
305
+ "<|begin_of_video|>",
306
+ "<|end_of_video|>",
307
+ "<|begin_of_audio|>",
308
+ "<|end_of_audio|>",
309
+ "<|begin_of_transcription|>",
310
+ "<|end_of_transcription|>",
311
+ "<|code_prefix|>",
312
+ "<|code_middle|>",
313
+ "<|code_suffix|>",
314
+ "/nothink"
315
+ ],
316
+ "clean_up_tokenization_spaces": false,
317
+ "do_lower_case": false,
318
+ "eos_token": "<|endoftext|>",
319
+ "extra_special_tokens": {},
320
+ "model_max_length": 131072,
321
+ "pad_token": "<|begin_of_video|>",
322
+ "padding_side": "left",
323
+ "remove_space": false,
324
+ "tokenizer_class": "PreTrainedTokenizerFast"
325
+ }