AMAImedia/Qwen3-32B-T-pro-it-2.1-NOESIS-AWQ-INT4
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: AMAImedia/Qwen3-32B-T-pro-it-2.1-NOESIS-AWQ-INT4
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 23:24:18 +08:00
commit 9666f81410
15 changed files with 2312 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

203
LICENSE Normal file
View File

@@ -0,0 +1,203 @@
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 2024 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.

187
README.md Normal file
View File

@@ -0,0 +1,187 @@
---
license: apache-2.0
language:
- ru
- en
- uk
- be
library_name: transformers
tags:
- awq
- int4
- quantization
- russian
- qwen3
- noesis
- dhcf-fno
base_model: t-tech/T-pro-it-2.1
quantized_by: AMAImedia
pipeline_tag: text-generation
---
# Qwen3-32B-T-pro-it-2.1-NOESIS-AWQ-INT4
**AWQ INT4 quantization of [t-tech/T-pro-it-2.1](https://huggingface.co/t-tech/T-pro-it-2.1)
optimized for low-VRAM consumer hardware via streaming inference.**
Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform**
(framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).
- **Founder:** Ilia Bolotnikov
- **Organization:** [AMAImedia.com](https://www.amaimedia.com)
- **X (Twitter):** [@AMAImediacom](https://x.com/AMAImediacom)
- **LinkedIn:** [Ilia Bolotnikov](https://www.linkedin.com/in/ilia-bolotnikov)
- **Telegram:** [@djbionicl](https://t.me/djbionicl)
- **NOESIS version:** v14.6
- **License:** Apache-2.0 (inherited from base model — fully permissive, commercial use allowed)
---
## ℹ️ Architecture clarification
T-pro-it-2.1 is a **dense Qwen3-32B model**, NOT a Mixture-of-Experts (MoE).
Upstream training used a SLERP merge of three GRPO-trained experts as a
**training-time technique**, but the resulting checkpoint is a single set of
dense weights with one forward pass and no router. This release follows
that architecture exactly — there are no expert layers, no gating networks,
and no conditional computation.
---
## Model summary
| Property | Value |
| --- | --- |
| Base model | t-tech/T-pro-it-2.1 |
| Underlying architecture | Qwen3-32B (decoder-only transformer, 64 layers, **dense**) |
| Original precision | BF16 safetensors (~64 GB) |
| Quantized precision | AWQ INT4 (group_size=128, GEMM, zero_point=True) |
| Vocab size | 151936 |
| Languages | Russian (primary), English, Ukrainian, Belarusian |
| Disk footprint | ~8.5 GB |
| Inference VRAM (full-resident) | ~9 GB (does NOT fit 6 GB GPUs without streaming) |
| Inference VRAM (streaming) | ~3.4 GB peak (per-layer offload — fits 6 GB GPU) |
| Quantization library | AutoAWQ 0.2.9 |
| Calibration set | 128 prompts (70% RU / 20% EN / 10% code), max_seq_len=512 |
| RNG seed | 1729 (NOESIS reproducibility lock) |
---
## Key feature: 6 GB GPU compatibility via streaming
Standard AWQ-INT4 of a 32B model needs ~9 GB VRAM, which excludes RTX 3060 / 4060
class hardware. **NOESIS ships a per-layer weight-streaming inference path**
where individual transformer layers are streamed from CPU RAM onto the GPU
on demand, executed, and freed. Peak VRAM stays at **~3.4 GB**, well inside
the SEALED 4.5 GB NOESIS specialist window.
Throughput on RTX 3060 (i7-12700H, DDR5-4800):
- Prefill: ~25 tok/s
- Per-layer load overhead: ~7 ms × 64 layers = 0.45 s amortized per batch
Suitable for: KD logits extraction, batch inference, offline summarization.
For low-latency interactive chat use the same checkpoint on a 12 GB+ GPU
in standard AutoAWQ inference mode.
---
## How to use
**Standard inference (12 GB+ GPU):**
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
import torch
model_id = "amaimedia/Qwen3-32B-T-pro-it-2.1-NOESIS-AWQ-INT4"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoAWQForCausalLM.from_quantized(
model_id,
device_map={"": 0},
torch_dtype=torch.float16,
fuse_layers=False,
)
messages = [
{"role": "system", "content": "Ты T-pro, полезный ассистент."},
{"role": "user", "content": "Объясни принцип работы трансформера."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
out = model.generate(
**inputs,
max_new_tokens=512,
temperature=0.7, top_p=0.8, top_k=20,
repetition_penalty=1.0,
)
print(tokenizer.decode(out[0], skip_special_tokens=True))
```
Recommended generation parameters per upstream T-Tech guidance:
`temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.0`.
Both `temperature` and `presence_penalty` should be set explicitly.
**Streaming inference (6 GB GPU):** see the NOESIS `extract_kd_streaming.py`
reference implementation.
---
## NOESIS context
In NOESIS this model serves as the **Russian-language teacher** for several
specialists during knowledge distillation:
| Target specialist | Role | Proposed KD weight |
| --- | --- | --- |
| M2-DUB-LM-10B | Dubbing LM (Russian segments) | 0.18 |
| M4-CHAT-10B | Chat / creative writing (Russian) | 0.18 |
| M9-ORCH-4B | Orchestrator (Russian routing) | 0.15 |
Vocab match (151936) is identical to the NOESIS base (Qwen3-8B), enabling
**direct logit alignment** without cross-tokenizer projection — a critical
property for clean KD on Russian shards.
---
## Quantization details
Calibration distribution:
- 70% Russian: chat, technical instruction, scientific exposition, creative writing
- 20% English: technical & instructional
- 10% Code: Python, Rust (RU and EN comments)
Quantization performed on:
- CPU: Intel i7-12700H (14 cores)
- RAM: 64 GB DDR5
- GPU: RTX 3060 6 GB (per-layer scale search)
- Disk offload: NVMe (`B:\noesis_offload_tpro\`, freed after quantization)
Wall time: ~3.5 hours.
---
## Acknowledgements & citation
Base model:
```bibtex
@misc{stoianov2025tpro20,
title = {T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground},
author = {Dmitrii Stoianov and Danil Taranets and Olga Tsymboi and others},
year = {2025},
eprint = {2512.10430},
archivePrefix = {arXiv}
}
```
Quantization & NOESIS integration:
```bibtex
@misc{noesis_v14,
title = {NOESIS v14.6: DHCF-FNO Multilingual Dubbing Platform},
author = {Bolotnikov, Ilia},
year = {2026},
publisher = {AMAImedia},
url = {https://amaimedia.com}
}
```

86
chat_template.jinja Normal file
View File

@@ -0,0 +1,86 @@
{%- 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 %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- 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" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- 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<think>\n\n</think>\n\n' }}
{%- endif %}

107
config.json Normal file
View File

@@ -0,0 +1,107 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151644,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 64,
"model_type": "qwen3",
"num_attention_heads": 64,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 8956,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.0.dev0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151689
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"do_sample": true,
"eos_token_id": 151644,
"pad_token_id": 8956,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.6.0.dev0"
}

3
model-00001-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1eb7a4027f54b90660227997c301c224753e125020044e5a01cfd66864e98431
size 3950491448

3
model-00002-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:99511fe81e35fd57a0331abc116e4562d9839f60feb8789f98b57597c31384f4
size 3985359072

3
model-00003-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82828d7c568987f014a1896497a43d9d65fb9b25f363b93dfdbfc8aab7ff8d5c
size 3936307144

3
model-00004-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f827f37fdb34541c058b550c09d90adbe685a4058da3126fab0ceb7591fab64
size 3985359104

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9fb058214caa894e74fbc1d63c5f51f3b11dc837cb6de177a0750aabf1a4571
size 3462905888

1610
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

41
noesis_provenance.json Normal file
View File

@@ -0,0 +1,41 @@
{
"noesis_version": "v14.1",
"framework": "DHCF-FNO",
"founder": "Ilia Bolotnikov",
"organization": "AMAImedia.com",
"source_model": "t-tech/T-pro-it-2.1",
"source_format": "BF16 safetensors",
"source_license": "Apache-2.0",
"base_model": "Qwen/Qwen3-32B",
"architecture": "Qwen3ForCausalLM (DENSE decoder-only, NOT MoE; 3 GRPO experts SLERP-merged offline into single weights)",
"vocab_size": 151936,
"languages": [
"ru",
"en",
"uk",
"be"
],
"quantization": {
"method": "AWQ",
"library": "autoawq 0.2.9",
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
},
"calibration": {
"samples": 128,
"max_seq_len": 512,
"domain_mix": {
"ru": 0.7,
"en": 0.2,
"code": 0.1
},
"source": "in-memory synthetic prompts (NOESIS internal)"
},
"specialist_role": "M2-DUB-LM (RU), M4-CHAT (RU), M9-ORCH (RU)",
"kd_weight_proposed": 0.18,
"kd_shard": "russian_only",
"rng_seed": 1729,
"torch_dtype_quant": "bfloat16"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:435644660964bf6006250f7c490579d1911e0442dfb3dcfac3f390abb241bd9a
size 13040407

14
tokenizer_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}