Dynamical-Systems/Dynamical-30B-A3B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Dynamical-Systems/Dynamical-30B-A3B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-03 16:50:20 +08:00
commit c5fc35f214
28 changed files with 171097 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

202
LICENSE Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2025 Alibaba Cloud
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

150
README.md Normal file
View File

@@ -0,0 +1,150 @@
---
language:
- en
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3-30B-A3B-Instruct-2507
tags:
- qwen3
- qwen3-moe
- reinforcement-learning
- scientific-judgment
- autonomous-science
- materials-discovery
- verified-environments
- multi-turn-reasoning
---
# Dynamical-30B-A3B
A trained judgment layer for autonomous scientific workflows. Starting from `Qwen/Qwen3-30B-A3B-Instruct-2507`, this model was trained with multi-turn reinforcement learning in verified campaign environments to improve sequential decision-making under uncertainty at the planner-verifier boundary.
The target capability is not general reasoning or autonomous science. It is the decision-making core that determines whether a larger scientific system behaves intelligently when search, evidence, cost, and belief updates are all coupled: selecting which candidate to investigate, evaluating whether evidence should be trusted or escalated, and revising hypotheses as conflicting results accumulate.
## Release Links
- **Paper PDF:** [Training Scientific Judgment with Verified Environments for Autonomous Science](https://github.com/Dynamical-Systems-Research/training-scientific-judgment/blob/main/paper/training-scientific-judgment.pdf)
- **Blog post:** [Training Scientific Judgment](https://dynamicalsystems.ai/blog/training-scientific-judgment)
- **Public repo:** [Dynamical-Systems-Research/training-scientific-judgment](https://github.com/Dynamical-Systems-Research/training-scientific-judgment)
- **Released evaluation bundle:** [repo `data/open_world/`](https://github.com/Dynamical-Systems-Research/training-scientific-judgment/tree/main/data/open_world)
- **Search assets:** [`Dynamical-Systems/crystalite-base`](https://huggingface.co/Dynamical-Systems/crystalite-base), [`Dynamical-Systems/crystalite-balanced`](https://huggingface.co/Dynamical-Systems/crystalite-balanced)
This model is the released **scientific-judgment policy** used in the final paper and blog post. The associated Crystalite checkpoints are released as supporting search-side assets for the open-world campaign provenance. The default public reproducibility path uses the frozen serialized campaign bundle from the public repo.
## Training
**Base model:** Qwen3-30B-A3B-Instruct-2507 (30B total / 3B active MoE)
**Stage 1 -- Supervised fine-tuning:** LoRA rank 32 on 3,861 rollout rows from GPT-5.4 teacher demonstrations across 128 closed-world environments. SFT establishes the action contract and baseline scientific behavior.
**Stage 2 -- Trajectory GRPO on open-world environments:** 247 training environments (741 entries across 3 seeds), 100 gradient steps with G=4. The RL stage teaches experiential decision-making: when to search vs. exploit existing candidates, when to trust vs. escalate evidence, and when to revise beliefs.
The curriculum uses a staged bucket schedule over environment difficulty:
- Steps 0--9: anchor-heavy warmup (75% anchor, 20% challenge)
- Steps 10--24: broadening (40% anchor, 30% challenge, 25% stress-discriminative)
- Steps 25--100: hard transfer regime (25% anchor, 30% challenge, 35% stress-discriminative, 10% stress-search-fragile)
Budget tiers expand across stages from (5, 8) to the full range (5, 8, 11, 14, 18).
**Reward:** Hybrid oracle + rubric. A physics-grounded oracle (thermodynamic stability from the MP2020 convex hull) provides manipulation-proof outcome reward. Rubric-based process supervision scores search quality, validation discipline, escalation efficiency, and revision quality via Gemini 3.1 Pro, gated on correctness.
This release corresponds to the **step-100 merged checkpoint**.
## Results
Primary metric: **hypothesis accuracy** -- the fraction of episodes where the model's highest-posterior hypothesis matches the oracle ground truth after all evidence rounds.
The final public release is paired with a frozen open-world bundle containing `300` serialized campaigns overall, with the primary paper evaluation reported on the pruned reachable held-out set of `29` campaigns.
### Held-out learning curve (29 open-world environments, pass@1)
| Checkpoint | Hypothesis Accuracy | Mean Reward | Parse Rate |
|---|---|---|---|
| Step 0 (SFT baseline) | 55.17% (16/29) | 0.3404 | 0.978 |
| Step 25 | 65.52% (19/29) | 0.4076 | 0.982 |
| Step 50 | 68.97% (20/29) | 0.4460 | 0.993 |
| Step 75 | **79.31% (23/29)** | 0.4801 | 0.981 |
| Step 100 | **79.31% (23/29)** | 0.5001 | 0.983 |
Total gain from SFT baseline: **+24.14 percentage points** across 100 RL steps. Step 100 matches step 75 in accuracy but achieves +4.2% higher reward and 33% lower truncation, indicating more efficient trajectories at the same correctness level.
### Per-round accuracy (survival curve)
RL fundamentally changes how accuracy relates to investigation depth. The SFT model's accuracy is flat-to-declining across campaign rounds (0.55 at round 0, dropping to 0.33 by round 10+). The RL model's accuracy increases monotonically with depth: 0.79 at round 0, rising to 1.0 by round 7. Episodes that investigate deeper are the ones that converge to the correct answer.
## What RL Teaches
Behavioral analysis of the trained policy reveals three learned capabilities absent in the SFT baseline.
**Search-then-exploit.** The RL model uses `skip_search` in 76.5% of search turns, learning to search once or twice to populate the candidate pool, then exploit existing candidates rather than wasting budget on redundant search. High-reward trajectories show strategic hypothesis switching -- searching for one system, pivoting to another, then returning.
**Suspect-then-decide validation.** The clearest RL signature is learned evidence escalation. Rather than blanket-rejecting all evidence (the SFT default), the RL model develops a two-step pattern: flag evidence as `suspect` to gather additional signal, then commit to `trust` or `reject`. Among the highest-reward trajectories, 100% use this pattern; among the lowest-reward, 0% do.
**Revision as a failure signal, not a tool.** In the SFT model, belief revision correlates with incorrect outcomes (wrong episodes average 2.1 revise turns vs 0.4 for correct). After RL, the 10 episodes that flipped from wrong to correct reduced their revision turns from 1.8 to 0.6. RL eliminates unnecessary revision by improving upstream search and validation, so the model arrives at the correct hypothesis without needing to update beliefs.
## Intended Use
This model is intended for research use in:
- Autonomous science agents requiring structured decision-making
- Budget-constrained experimental planning and evidence triage
- Multi-step scientific judgment under uncertainty
- Studies of post-training for sequential decision-making
It operates as a judgment policy within a larger workflow that provides candidate generation, structured evidence, and domain-specific verification oracles.
## Limitations
- **Single training seed.** Results are from one training run. The learning curve shape (acceleration at steps 50--75) has not been validated across seeds.
- **Evaluation scale.** The primary evaluation uses 29 held-out environments with pass@1. Per-budget and per-difficulty analyses have limited statistical power.
- **Staged verifier.** Cheap and medium evidence stages are transforms of E_hull, not independent physical measurements.
- **Persistent failures.** 6 of 29 held-out episodes remain incorrect. Failure modes include budget exhaustion on sparse search pools, RL-induced regressions on easy specifications, and contaminated evidence that passes the suspect filter.
- **Not a substitute for expert review.** This model should not replace physical simulation, laboratory verification, or domain expertise in high-stakes scientific decisions.
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Dynamical-Systems/Dynamical-30B-A3B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [
{
"role": "user",
"content": "Given these candidates and staged measurements, which one should we validate next, and should we trust or escalate the current evidence?"
}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))
```
## Citation
```bibtex
@misc{barnes2026trainingscientificjudgment,
title={Training Scientific Judgment with Verified Environments for Autonomous Science},
author={Jarrod Barnes},
year={2026},
note={Technical report preprint}
}
```
## Acknowledgments
Dynamical-30B-A3B is derived from `Qwen/Qwen3-30B-A3B-Instruct-2507` and retains the upstream Apache 2.0 license. Training infrastructure provided by [Tinker](https://tinker.computer).

61
chat_template.jinja Normal file
View File

@@ -0,0 +1,61 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# 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>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\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" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 262144,
"max_window_layers": 48,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000000,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

45
config_1m.json Normal file
View File

File diff suppressed because one or more lines are too long

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.51.0"
}

151387
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc59f154d0e7dcb88587534cf0d7d5495b8ca283cda1e8e1a9a1c96001c975e1
size 3998893080

3
model-00002-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf65611535f3fe1ff68d8fc19cdd4296d7763628904e802bf3bcf6a7eec26e9c
size 3999974160

3
model-00003-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a81e18d826226159f636b4052c3dd073be162c9449ffc47f401e0a60ffd4b018
size 3997360800

3
model-00004-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3fd3338bcec105ce69a4d9b411a22ef55ce1374dbd7539c313540fd56ed37cd
size 3999975024

3
model-00005-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:708e48af54a79afc523ce5f813b42b24c86c677dc96c88880b482e70a632d214
size 3999975368

3
model-00006-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdd2243e02b57b9515a2d18f521cf76a9fc9b6e45ba93354d9c100edcf49ff91
size 3999975368

3
model-00007-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d67b655dc06d86a981c8102984e2354e679a38312095de95c331d19e37b0c6c
size 3999975440

3
model-00008-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ad8026d5809cad1a89a377731dd236296e22e1782c271daf0902123a75e0403
size 3997362032

3
model-00009-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05788fa30dfabdac814a64314ed9dea620fcf037f965f98d527813a47c5bcdd4
size 3999975376

3
model-00010-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0e0a01d71f07476063979088e2024754629474dd3c6cc713a93b9cfb38ee454
size 3999975368

3
model-00011-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21b368c4cf8afba0421943475d2b23422fddc500f157d088781dbc245de94aea
size 3999975376

3
model-00012-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c82d15aafab78f2e9be5b5e1a2e5c78653fc86d56da653b44c94c8d012c037bd
size 3987924864

3
model-00013-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21873a9e81180cc5e8787264c2028763627bfc8571b0a2ad320757709ae71ebe
size 3999975056

3
model-00014-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3aebad36903748245993a95b0d0a79164651caf8a337579c2132aa3c86869614
size 3999975368

3
model-00015-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d434a1df82b31028b1b41e229c76811704edf2c5466a4e4ef74c946d90255b80
size 3999975368

3
model-00016-of-00016.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d31efef2b520ac32158ab4c0346e65dc2430619c543d0bd151be35e1333f82c4
size 1085307096

18874
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

239
tokenizer_config.json Normal file
View File

@@ -0,0 +1,239 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 1010000,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"add_bos_token": false
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long