初始化项目,由ModelHub XC社区提供模型

Model: srs6901/Vikras-1-to-3b-collection
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-20 02:10:24 +08:00
commit d7b2ea0a4a
51 changed files with 257422 additions and 0 deletions

43
.gitattributes vendored Normal file
View File

@@ -0,0 +1,43 @@
*.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
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf filter=lfs diff=lfs merge=lfs -text
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Vikra-HCT-YeAM-PhiMma-1B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
YeAM_Llama32-1B_Instruct_X2_DENOISED-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
YeAM_Llama32-1B_Instruct_X2_DENOISED/tokenizer.json filter=lfs diff=lfs merge=lfs -text

173
README.md Normal file
View File

@@ -0,0 +1,173 @@
---
library_name: transformers
tags:
- quantized
- custom
- nonlinear
- mixed-precision
- merged
- MoK
language:
- ru
- en
metrics:
- perplexity
pipeline_tag: text-generation
---
# Vikras — Experimental Family of Language Models
[EN below](#vikras--experimental-family-of-language-models-en)
## Содержание
- [Коротко о проекте](#коротко-о-проекте)
- [Что это за репозиторий](#что-это-за-репозиторий)
- [Текущий релиз: HCT/YeAM (1-3B)](#текущий-релиз-hctyeam-1-3b)
- [HCT (архитектура) / YeAM (инвариант реализации)](#hct-архитектура--yeam-инвариант-реализации)
---
## Коротко о проекте
**Vikra** — экспериментальное семейство языковых моделей, исследующее влияние:
- геометрии представлений
- квантования
- гибридных мерджей
на численную динамику трансформеров.
Проект **Vikras** не ограничивается одной базой или одной архитектурой: это семейство моделей, объединённых идеей численной инвариантности эксперимента.
- **Vikra_%** — имя конкретной модели
- **Vikras** — семейство экспериментов
- **S / M / L** — степень агрессивности и распределения битности
- **MixP / FullP / HCT** — схемы и инварианты квантования/мерджей
---
## Что это за репозиторий
Это витрина моделей **Vikras** в диапазоне **13B**.
Здесь лежат только компактные релизы, которые можно относительно легко запускать локально.
Сноска на основной репозиторий (лаборатория/склад):
- https://huggingface.co/srs6901/Vikras-MixP
В основном репозитории релизы и эксперименты появляются быстрее, там же полный каталог (включая более крупные модели).
---
## Текущий релиз: HCT/YeAM (1-3B)
### Релизы
- **Vikra-HCT-YeAM-LLaGemma-1B**
- Что с чем: Llama-3.2-1B-Instruct + Gemma-3-1b-pt
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-LLaGemma-1B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
- **Vikra-HCT-YeAM-PhiMma-1B**
- Что с чем: Gemma-3-1b-pt + Microsoft Phi-2
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-PhiMma-1B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
- **Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B**
- Что с чем: Llama-3.2-1B-Instruct + Qwen3-1.7B (HCT/YeAM-производный релиз)
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
---
## HCT (архитектура) / YeAM (инвариант реализации)
**HCT** — архитектурный инвариант: практический способ собирать совместимые модели и производные релизы при переносе между базами/семействами.
**YeAM (Yet Another Merge)** — инвариант реализации HCT и самостоятельная схема мерджа HF→HF: это не «ещё один SLERP/DARE/TILES» и не косметическая вариация усреднения.
YeAM выдаёт стандартный HF-результат (safetensors + index) и поддерживает:
- прямой weight-to-weight мердж
- направленное добавление знаний в выбранную модель (knowledge distillation / knowledge injection), согласованное по нескольким источникам
- дополнительный мердж Attention-слоёв как отдельную технику поверх YeAM
- мердж меньших моделей в более крупные (scale-up merge) при сохранении совместимого HF-формата
Математически YeAM работает в **реальной 4D-постановке**: обновления кодируются геометрически и согласуются через пересечения лучей в пространстве параметров. Это даёт управляемый мердж с сохранением структуры и без вырождения в наивное усреднение.
---
# Vikras — Experimental Family of Language Models (EN)
## Table of Contents
- [Project overview](#project-overview)
- [What this repository is](#what-this-repository-is)
- [Current Release: HCT/YeAM (1-3B)](#current-release-hctyeam-1-3b)
- [HCT (architecture) / YeAM (implementation invariant)](#hct-architecture--yeam-implementation-invariant)
---
## Project overview
**Vikra** is an experimental family of language models exploring how:
- representation geometry
- quantization
- hybrid merges
affect transformer numerical dynamics.
The **Vikras** project is not tied to a single base model or architecture.
It is a family of models unified by a numerical invariance philosophy of experimentation.
- **Vikra_%** — a specific model
- **Vikras** — the experimental family
- **S / M / L** — aggressiveness and bit allocation variants
- **MixP / FullP / HCT** — quantization / merge invariants
---
## What this repository is
This is a curated **13B** showcase for the **Vikras** family.
Only compact releases are mirrored here.
Footnote / main repository (lab + full catalog):
- https://huggingface.co/srs6901/Vikras-MixP
The main repository is updated faster and contains the complete set of experiments (including larger models).
---
## Current Release: HCT/YeAM (1-3B)
### Releases
- **Vikra-HCT-YeAM-LLaGemma-1B**
- Merge recipe: Llama-3.2-1B-Instruct + Gemma-3-1b-pt
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-LLaGemma-1B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
- **Vikra-HCT-YeAM-PhiMma-1B**
- Merge recipe: Gemma-3-1b-pt + Microsoft Phi-2
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-PhiMma-1B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
- **Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B**
- Merge recipe: Llama-3.2-1B-Instruct + Qwen3-1.7B (HCT/YeAM-derived release)
- HF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/tree/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B
- GGUF: https://huggingface.co/srs6901/Vikras-1-to-3b-collection/blob/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
---
## HCT (architecture) / YeAM (implementation invariant)
**HCT** is an architectural invariant — a practical way to assemble compatible checkpoints and derived releases while moving across bases / model families.
**YeAM (Yet Another Merge)** is an implementation invariant of HCT and a standalone HF→HF merge scheme: it is not “just another SLERP/DARE/TILES” and not a cosmetic variant of averaging.
YeAM produces a standard HF output (safetensors + index) and supports:
- direct weight-to-weight merging
- targeted knowledge injection into a chosen model (knowledge distillation mode), aligned across multiple sources
- an additional Attention-layer merge as a second technique on top of YeAM
- merging smaller models into larger ones (scale-up merge) while keeping a compatible HF format
YeAM operates in a **real 4D formulation**: updates are encoded geometrically and aligned via ray intersections in parameter space. This produces controlled merges that preserve structure instead of collapsing into naive averaging.
---

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 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.

View File

@@ -0,0 +1,69 @@
---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3-1.7B-Base
---
# Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B
HCT architecture release. YeAM (Yet Another Merge) implementation invariant.
## What it is
A compact 1.7B-class checkpoint produced via HCT-compatible merging.
The checkpoint is published in standard Hugging Face format (safetensors + index).
## YeAM summary
YeAM performs a controlled merge in a real 4D geometric formulation with ray-intersection alignment in parameter space.
It also supports targeted knowledge injection (distillation-style) into a chosen model while remaining HF-compatible.
## Notes for this checkpoint
Compared to other YeAM/HCT merges, this checkpoint additionally applies a targeted merge on Attention projection weights.
Observed behavior tends to include characteristic Llama-like traits:
- More Llama-style conversation patterns.
- More consistent formatting.
- Stronger RLHF-like refusal/priority behaviors.
- Reasoning / chain-of-thought style output in the model's full native format is expected to work.
At the same time, most Qwen3 behavior should theoretically remain, but due to knowledge/logic injection from the Llama side, some Qwen-specific properties may be partially degraded or inconsistent.
Repetition / looping:
- There is no universally perfect sampling configuration.
- At higher temperature, without a repetition-style penalty, the model may enter repetition loops.
- Pay special attention to repetition-related controls (e.g. repetition penalty / presence penalty) if you observe cycling.
Do not ask the model who created it.
In this specific merge, it may oscillate between incompatible parents (Alibaba vs Meta”), fail to settle, and get stuck in a sad loop.
## Usage (Transformers)
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
m = "/path/to/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B"
tok = AutoTokenizer.from_pretrained(m, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
m,
torch_dtype=torch.bfloat16,
device_map="cuda",
).eval()
inputs = tok("Hello!", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
```
## GGUF
Convert and quantize with llama.cpp (example):
```bash
python3 /path/to/llama.cpp/convert_hf_to_gguf.py /path/to/model --outtype f16 --outfile model.f16.gguf
/path/to/llama.cpp/build/bin/llama-quantize model.f16.gguf model.Q8_0.gguf Q8_0
```

View File

@@ -0,0 +1,30 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.51.0"
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c76fa123a80c02c23b893f5f70b5261371826def47d7141b2c2375eb0923a92d
size 1244659944

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44210ebae89ff50ed223b66c48fb5bd3da690983ce3b10cc76289f89b9c2085b
size 1082234512

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e54f9d3e91602558c7b53caeb8061dbcb726959a5c9ee30f3e27e99716a50b0
size 1082239816

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b96e907df89c1934843aeb61b26a84b805b339ab04dfb831ffef903b6112b817
size 654380800

File diff suppressed because one or more lines are too long

BIN
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,239 @@
{
"add_bos_token": false,
"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{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- 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>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\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 {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5c3eab905f68c6f9001d3af2c17c538a1583e6804106d048e0a2b0ca881cd7c
size 2165039488

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:106774be0e59d7939904784f171932c95b759fdbe979948a6df143c966903ea3
size 1069306496

View File

@@ -0,0 +1,50 @@
---
license: gemma
library_name: transformers
pipeline_tag: text-generation
base_model: google/gemma-3-1b-pt
---
# Vikra-HCT-YeAM-LLaGemma-1B
Llama-3.2-1B-Instruct + Gemma-3-1b-pt
HCT architecture release. YeAM (Yet Another Merge) implementation invariant.
## What it is
A compact 1B-class model produced via HCT-compatible merging.
The checkpoint is published in standard Hugging Face format (safetensors + index).
## YeAM summary
YeAM performs a controlled merge in a real 4D geometric formulation with ray-intersection alignment in parameter space.
It also supports targeted knowledge injection (distillation-style) into a chosen model while remaining HF-compatible.
## Usage (Transformers)
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
m = "/path/to/Vikra-HCT-YeAM-LLaGemma-1B"
tok = AutoTokenizer.from_pretrained(m, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
m,
torch_dtype=torch.bfloat16,
device_map="cuda",
).eval()
inputs = tok("Hello!", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
```
## GGUF
Convert and quantize with llama.cpp (example):
```bash
python3 /path/to/llama.cpp/convert_hf_to_gguf.py /path/to/model --outtype bf16 --outfile model.bf16.gguf
/path/to/llama.cpp/build/bin/llama-quantize model.bf16.gguf model.Q6_K.gguf Q6_K
```

View File

@@ -0,0 +1,3 @@
{
"<image_soft_token>": 262144
}

View File

@@ -0,0 +1,37 @@
{
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": [
1,
106
],
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 26,
"num_key_value_heads": 1,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": 512,
"sliding_window_pattern": 6,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0.dev0",
"use_cache": true,
"vocab_size": 262144
}

View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 2,
"cache_implementation": "hybrid",
"do_sample": true,
"eos_token_id": [
1,
106
],
"pad_token_id": 0,
"top_k": 64,
"top_p": 0.95,
"transformers_version": "4.50.0.dev0"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d327513594d6e96139c1660d5389b20cc9de3797796b69ca9cb8d21ad420c31
size 1081244120

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff4980829a32e0feccf675d107ffc2ebc495139577c3ce7460ffc3a0fe8ff76f
size 918566568

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,33 @@
{
"boi_token": "<start_of_image>",
"bos_token": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eoi_token": "<end_of_image>",
"eos_token": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"image_token": "<image_soft_token>",
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
size 33384568

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
size 4689074

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cc9a6638b222213cc705401efb8d4ae2aac38bb0c25f4c3315d64be3d6587aa
size 1069306496

View File

@@ -0,0 +1,49 @@
---
license: gemma
library_name: transformers
pipeline_tag: text-generation
base_model: google/gemma-3-1b-pt
---
# Vikra-HCT-YeAM-PhiMma-1B
Gemma-3-1b-pt + Microsoft_phi-2
HCT architecture release. YeAM (Yet Another Merge) implementation invariant.
## What it is
A compact 1B-class model produced via HCT-compatible merging.
The checkpoint is published in standard Hugging Face format (safetensors + index).
## YeAM summary
YeAM performs a controlled merge in a real 4D geometric formulation with ray-intersection alignment in parameter space.
It also supports targeted knowledge injection (distillation-style) into a chosen model while remaining HF-compatible.
## Usage (Transformers)
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
m = "/path/to/Vikra-HCT-YeAM-PhiMma-1B"
tok = AutoTokenizer.from_pretrained(m, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
m,
torch_dtype=torch.bfloat16,
device_map="cuda",
).eval()
inputs = tok("Hello!", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
```
## GGUF
Convert and quantize with llama.cpp (example):
```bash
python3 /path/to/llama.cpp/convert_hf_to_gguf.py /path/to/model --outtype bf16 --outfile model.bf16.gguf
/path/to/llama.cpp/build/bin/llama-quantize model.bf16.gguf model.Q6_K.gguf Q6_K
```

View File

@@ -0,0 +1,3 @@
{
"<image_soft_token>": 262144
}

View File

@@ -0,0 +1,37 @@
{
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": [
1,
106
],
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 26,
"num_key_value_heads": 1,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": 512,
"sliding_window_pattern": 6,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0.dev0",
"use_cache": true,
"vocab_size": 262144
}

View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 2,
"cache_implementation": "hybrid",
"do_sample": true,
"eos_token_id": [
1,
106
],
"pad_token_id": 0,
"top_k": 64,
"top_p": 0.95,
"transformers_version": "4.50.0.dev0"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd10088d6f4ea7bd681d61f3ae77b02e6202587e0817b5d91dad2e949bf248b7
size 1081244120

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15d8aa3dfd280419d37ea5b3e79ea12aabf419cf96cbc11b17c8f4c9bb5a4aaa
size 918566568

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,33 @@
{
"boi_token": "<start_of_image>",
"bos_token": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eoi_token": "<end_of_image>",
"eos_token": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"image_token": "<image_soft_token>",
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
size 33384568

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
size 4689074

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bca3eda347602d7d3278ec58c2d569e189bfe4a453b0831f15ad3eba8747fb6
size 1321082656

View File

@@ -0,0 +1,93 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- if strftime_now is defined %}
{%- set date_string = strftime_now("%d %b %Y") %}
{%- else %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{{- "<|eot_id|>" }}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

View File

@@ -0,0 +1,37 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"pad_token_id": 128004,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.0.dev0",
"unsloth_fixed": true,
"use_cache": true,
"vocab_size": 128256
}

View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"max_length": 131072,
"pad_token_id": 128004,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.52.0.dev0"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b11bb530609f86f963b3ab84714bdc615577b35f639c92f2342749f8ac3a3d1
size 1079026152

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd45477e250d89441c6804c035e1e002893f769a2918c2a44901b349d7e141c4
size 1094796312

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94e27e42ad3005b9208bebf45ecfe522a20e615e7bb6a34f512457de3ab16c38
size 297822992

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|finetune_right_pad_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
YeAM_Llama32-1B_Instruct_X2_DENOISED/tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

File diff suppressed because it is too large Load Diff