初始化项目，由ModelHub XC社区提供模型
Model: srs6901/Vikras-MixP Source: Original Platform
This commit is contained in:
ModelHub XC
44
.gitattributes
vendored
Normal file
44
.gitattributes
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
*.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-MixP_4.9b_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Vikra-MixedP-MXFP4.gguf 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
|
||||
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf 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
|
||||
463
README.md
Normal file
463
README.md
Normal file
@@ -0,0 +1,463 @@
|
||||
---
|
||||
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)
|
||||
- [Текущий релиз: HCT/YeAM](#текущий-релиз-hctyeam)
|
||||
- [HCT (архитектура) / YeAM (инвариант реализации)](#hct-архитектура--yeam-инвариант-реализации)
|
||||
- [Предыдущий релиз: Vikra MixedPrc (MixP_4.9b_S)](#предыдущий-релиз-vikra-mixedprc-mixp_49b_s)
|
||||
- [MixP_4.9b_S: детали](#mixp_49b_s-детали)
|
||||
- [Планы развития](#планы-развития)
|
||||
- [Использование](#использование)
|
||||
- [Заключение](#заключение)
|
||||
|
||||
---
|
||||
|
||||
## 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
|
||||
|
||||
---
|
||||
|
||||
## Текущий релиз: HCT/YeAM
|
||||
|
||||
### Релизы
|
||||
|
||||
- **Vikra-HCT-YeAM-PhiMma-1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-PhiMma-1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
|
||||
- **Vikra-HCT-YeAM-LLaGemma-1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-LLaGemma-1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
|
||||
- **Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
|
||||
- **Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_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.
|
||||
|
||||
---
|
||||
|
||||
## Предыдущий релиз: Vikra MixedPrc (MixP_4.9b_S)
|
||||
|
||||
### Краткое описание
|
||||
|
||||
12.25B Mistral-based language model
|
||||
Hybrid mixed-precision merged GGUF quantization
|
||||
Экспериментальный режим анизотропного квантования
|
||||
|
||||
Полная версия мерджа (без квантования):
|
||||
https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-FullP
|
||||
|
||||
GGUF-квант:
|
||||
https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-MixP_4.9b_S.gguf
|
||||
|
||||
---
|
||||
|
||||
## MixP_4.9b_S: детали
|
||||
|
||||
### Архитектура (для MixP релиза)
|
||||
|
||||
| Параметр | Значение |
|
||||
|---|---|
|
||||
| Architecture | Mistral-based |
|
||||
| Params | ~12.25B |
|
||||
| Layers | 40 |
|
||||
| Hidden size | 5120 |
|
||||
| FFN size | 14336 |
|
||||
| Heads | 32 (8 KV heads, GQA) |
|
||||
| Context | 1,024,000 |
|
||||
| Vocab | 131,072 (Tekken BPE) |
|
||||
| RoPE theta | 1,000,000 |
|
||||
|
||||
### MixP_4.9b_S — схема квантования
|
||||
|
||||
Гибридная mixed precision схема с покомпонентным распределением типов.
|
||||
|
||||
| Tensor group | Quant type | BPW |
|
||||
|---|---|---|
|
||||
| token_embd, output | BF16 | 16 |
|
||||
| attn_norm, ffn_norm, output_norm | F32 | 32 |
|
||||
| attn_q | Q4_K | 4.5 |
|
||||
| attn_k | Q5_K | 5.5 |
|
||||
| attn_v | Q3_K | 3.44 |
|
||||
| attn_output | Q4_K | 4.5 |
|
||||
| ffn_gate | Q3_K | 3.44 |
|
||||
| ffn_up | Q5_K | 5.5 |
|
||||
| ffn_down | Q5_K / Q6_K | 5.5–6.56 |
|
||||
|
||||
Итого:
|
||||
|
||||
- Quantized layers only: ~4.89 BPW
|
||||
- Full model average: ~6.11 BPW
|
||||
- File size: ~8.71 GB
|
||||
|
||||
### Ключевая идея MixP
|
||||
|
||||
MixP — это не «сжать всё одинаково».
|
||||
|
||||
Это **анизотропное квантование информационных каналов**:
|
||||
|
||||
• Q/K сохраняются в более высокой точности
|
||||
• V и gate намеренно квантованы до Q3_K
|
||||
• Нормы и выходной слой остаются в высокой точности
|
||||
|
||||
Такое распределение изменяет численную динамику модели:
|
||||
|
||||
• усиливается структурная sparsification
|
||||
• меняется распределение норм скрытых представлений
|
||||
• меняется энтропия логитов
|
||||
• появляется режимная чувствительность
|
||||
|
||||
Это не новая архитектура.
|
||||
Это изменение численной геометрии существующей.
|
||||
|
||||
### Наблюдаемые эффекты
|
||||
|
||||
- сохранение top-1 предсказаний на простых задачах
|
||||
- рост entropy без разрушения максимальной вероятности
|
||||
- расширение hidden norm на сложных задачах
|
||||
- бифуркация режимов: простые задачи ≈ инвариантны, сложные — чувствительны
|
||||
|
||||
Эти эффекты описываются как геометрический сдвиг представлений, а не как универсальное улучшение качества.
|
||||
|
||||
|
||||
### math_subattention (рабочая гипотеза)
|
||||
|
||||
В экспериментах наблюдается эффект, условно обозначенный как:
|
||||
|
||||
“math_subattention”
|
||||
|
||||
Под этим подразумевается:
|
||||
|
||||
• уменьшение вклада мелких компонент V
|
||||
• усиление доминирующих направлений residual stream
|
||||
• повышенная инерция предыдущего токена
|
||||
• снижение частоты мелких переключений логитов
|
||||
|
||||
Это не claim о новой архитектуре.
|
||||
Это рабочая гипотеза о динамике, возникающей при Q3_K symmetric quantization.
|
||||
|
||||
Термин используется описательно.
|
||||
|
||||
### Перплексия
|
||||
|
||||
Метрика измерена на wikitext-2-raw-test (full):
|
||||
|
||||
| Model | Precision | PPL |
|
||||
|---|---|---|
|
||||
| Vikra MixP_4.9b_S | 6.11 BPW | 5.50 ± 0.03 |
|
||||
| Baseline BF16 | Full | 6.02 ± 0.03 |
|
||||
|
||||
---
|
||||
|
||||
## Планы развития
|
||||
|
||||
Планируются подсемейства:
|
||||
|
||||
- MixP — Mixed Precision
|
||||
- FullP — Full Precision версии
|
||||
- HCT — multi-merge эксперименты
|
||||
- S / M / L — варианты распределения битности
|
||||
|
||||
Все модели семейства называются **Vikra**.
|
||||
Репозиторий — **Vikras**.
|
||||
|
||||
---
|
||||
|
||||
## Использование
|
||||
|
||||
```bash
|
||||
llama-cli -m Vikra-MixP_4.9b_S.gguf -ngl 99 -c 4096
|
||||
```
|
||||
|
||||
```bash
|
||||
llama-server -m Vikra-MixP_4.9b_S.gguf -ngl 99 -c 4096
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Заключение
|
||||
|
||||
Vikras — исследовательский проект.
|
||||
|
||||
Он исследует, как меняется поведение трансформера, если его:
|
||||
|
||||
- сжимать
|
||||
- смешивать
|
||||
- изменять численную геометрию
|
||||
|
||||
Если вам интересны hidden space dynamics / regime sensitivity / anisotropic quantization — добро пожаловать.
|
||||
|
||||
---
|
||||
|
||||
# Vikras — Experimental Family of Language Models (EN)
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [Project overview](#project-overview)
|
||||
- [Current Release: HCT/YeAM](#current-release-hctyeam)
|
||||
- [HCT (architecture) / YeAM (implementation invariant)](#hct-architecture--yeam-implementation-invariant)
|
||||
- [Previous Release: Vikra MixedPrc (MixP_4.9b_S)](#previous-release-vikra-mixedprc-mixp_49b_s)
|
||||
- [MixP_4.9b_S: details](#mixp_49b_s-details)
|
||||
- [Roadmap](#roadmap)
|
||||
- [Usage](#usage)
|
||||
- [Closing](#closing)
|
||||
|
||||
---
|
||||
|
||||
## 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
|
||||
|
||||
---
|
||||
|
||||
## Current Release: HCT/YeAM
|
||||
|
||||
### Releases
|
||||
|
||||
- **Vikra-HCT-YeAM-PhiMma-1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-PhiMma-1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
|
||||
- **Vikra-HCT-YeAM-LLaGemma-1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-LLaGemma-1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
|
||||
- **Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
|
||||
- **Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B**
|
||||
- HF: https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B
|
||||
- GGUF: https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf
|
||||
|
||||
---
|
||||
|
||||
## HCT (architecture) / YeAM (implementation invariant)
|
||||
|
||||
**HCT** is an architectural invariant.
|
||||
In English: **Heterogeneous Compatibility Transfer** — 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.
|
||||
|
||||
---
|
||||
|
||||
## Previous Release: Vikra MixedPrc (MixP_4.9b_S)
|
||||
|
||||
### Short Description
|
||||
|
||||
12.25B Mistral-based language model
|
||||
Hybrid mixed-precision merged GGUF quantization
|
||||
Experimental anisotropic quantization regime
|
||||
|
||||
Full merge version (non-quantized):
|
||||
https://huggingface.co/srs6901/Vikras-MixP/tree/main/Vikra-FullP
|
||||
|
||||
GGUF quant:
|
||||
https://huggingface.co/srs6901/Vikras-MixP/blob/main/Vikra-MixP_4.9b_S.gguf
|
||||
|
||||
---
|
||||
|
||||
## MixP_4.9b_S: details
|
||||
|
||||
### Architecture (for the MixP release)
|
||||
|
||||
| Parameter | Value |
|
||||
|---|---|
|
||||
| Architecture | Mistral-based |
|
||||
| Params | ~12.25B |
|
||||
| Layers | 40 |
|
||||
| Hidden size | 5120 |
|
||||
| FFN size | 14336 |
|
||||
| Heads | 32 (8 KV heads, GQA) |
|
||||
| Context | 1,024,000 |
|
||||
| Vocab | 131,072 (Tekken BPE) |
|
||||
| RoPE theta | 1,000,000 |
|
||||
|
||||
### MixP_4.9b_S — Quantization Scheme
|
||||
|
||||
A hybrid mixed-precision scheme with per-tensor type allocation.
|
||||
|
||||
| Tensor group | Quant type | BPW |
|
||||
|---|---|---|
|
||||
| token_embd, output | BF16 | 16 |
|
||||
| attn_norm, ffn_norm, output_norm | F32 | 32 |
|
||||
| attn_q | Q4_K | 4.5 |
|
||||
| attn_k | Q5_K | 5.5 |
|
||||
| attn_v | Q3_K | 3.44 |
|
||||
| attn_output | Q4_K | 4.5 |
|
||||
| ffn_gate | Q3_K | 3.44 |
|
||||
| ffn_up | Q5_K | 5.5 |
|
||||
| ffn_down | Q5_K / Q6_K | 5.5–6.56 |
|
||||
|
||||
Totals:
|
||||
|
||||
- Quantized layers only: ~4.89 BPW
|
||||
- Full model average: ~6.11 BPW
|
||||
- File size: ~8.71 GB
|
||||
|
||||
### Core idea of MixP
|
||||
|
||||
MixP is not “compress everything equally”.
|
||||
|
||||
It is **anisotropic quantization of information channels**:
|
||||
|
||||
- Q/K remain in higher precision
|
||||
- V and gate are intentionally quantized down to Q3_K
|
||||
- norms and the output layer remain in higher precision
|
||||
|
||||
This redistribution changes the numerical dynamics of the model:
|
||||
|
||||
- increased structural sparsification
|
||||
- shifts in hidden norm distribution
|
||||
- changes in logit entropy
|
||||
- regime sensitivity
|
||||
|
||||
This is not a new architecture.
|
||||
It is a modification of the numerical geometry of an existing one.
|
||||
|
||||
### Observed effects
|
||||
|
||||
- preservation of top-1 predictions on simple tasks
|
||||
- increased entropy without collapse of maximum probability
|
||||
- expansion of hidden norms on complex tasks
|
||||
- mode bifurcation: simple tasks ≈ invariant, complex tasks sensitive
|
||||
|
||||
These effects are interpreted as a geometric shift of representations rather than a universal quality improvement.
|
||||
|
||||
### math_subattention (working hypothesis)
|
||||
|
||||
In experiments, an effect informally referred to as:
|
||||
|
||||
“math_subattention”
|
||||
|
||||
This describes:
|
||||
|
||||
- reduced contribution of small V components
|
||||
- dominance of stronger residual directions
|
||||
- increased inertia from previous token state
|
||||
- reduced frequency of small logit switching
|
||||
|
||||
This is not an architectural claim.
|
||||
It is a working hypothesis of dynamics emerging from Q3_K symmetric quantization.
|
||||
|
||||
The term is used descriptively.
|
||||
|
||||
### Perplexity
|
||||
|
||||
Measured on wikitext-2-raw-test (full):
|
||||
|
||||
| Model | Precision | PPL |
|
||||
|---|---|---|
|
||||
| Vikra MixP_4.9b_S | 6.11 BPW | 5.50 ± 0.03 |
|
||||
| Baseline BF16 | Full | 6.02 ± 0.03 |
|
||||
|
||||
---
|
||||
|
||||
## Roadmap
|
||||
|
||||
Planned subfamilies:
|
||||
|
||||
- MixP — Mixed Precision
|
||||
- FullP — Full Precision variants
|
||||
- HCT — multi-merge experiments
|
||||
- S / M / L — different bit allocation regimes
|
||||
|
||||
All models in the family are called **Vikra**.
|
||||
The repository is **Vikras**.
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
llama-cli -m Vikra-MixP_4.9b_S.gguf -ngl 99 -c 4096
|
||||
```
|
||||
|
||||
```bash
|
||||
llama-server -m Vikra-MixP_4.9b_S.gguf -ngl 99 -c 4096
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Closing
|
||||
|
||||
Vikras is a research project.
|
||||
|
||||
It explores how transformer behavior changes when we:
|
||||
|
||||
- compress
|
||||
- merge
|
||||
- alter numerical geometry
|
||||
|
||||
If you are interested in hidden space dynamics / regime sensitivity / anisotropic quantization — welcome.
|
||||
27
Vikra-FullP/config.json
Normal file
27
Vikra-FullP/config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072,
|
||||
"_name_or_path": "Vikra MixedPrc"
|
||||
}
|
||||
3
Vikra-FullP/model-00001-of-00005.safetensors
Normal file
3
Vikra-FullP/model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bad11922e79fff3687ad25e68c8746fa60e12c7b228d6810664bd51e4e732109
|
||||
size 4865489336
|
||||
3
Vikra-FullP/model-00002-of-00005.safetensors
Normal file
3
Vikra-FullP/model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8db601b1ed1d171d4bbccf02a451a85bbd46e2b4b68240cb6df58ecbf9376c0a
|
||||
size 4907529456
|
||||
3
Vikra-FullP/model-00003-of-00005.safetensors
Normal file
3
Vikra-FullP/model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1033a9661f0c78949f17034f7c3d526438b5eabd53fd6bc66c60e6d3be6b33e6
|
||||
size 4907529464
|
||||
3
Vikra-FullP/model-00004-of-00005.safetensors
Normal file
3
Vikra-FullP/model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb676dad5f501c2ff1bb9d2c953426ce6c63d4f68b5778ef6363442b24b0c044
|
||||
size 4907529456
|
||||
3
Vikra-FullP/model-00005-of-00005.safetensors
Normal file
3
Vikra-FullP/model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7972467102cca43624144be259da7ed0c470261f8d59d40783166b5180c77f06
|
||||
size 4907529392
|
||||
371
Vikra-FullP/model.safetensors.index.json
Normal file
371
Vikra-FullP/model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495564800,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00005.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
23
Vikra-FullP/special_tokens_map.json
Normal file
23
Vikra-FullP/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
409625
Vikra-FullP/tokenizer.json
Normal file
409625
Vikra-FullP/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
8014
Vikra-FullP/tokenizer_config.json
Normal file
8014
Vikra-FullP/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
202
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/LICENSE
Normal file
202
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/LICENSE
Normal 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.
|
||||
69
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/README.md
Normal file
69
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/README.md
Normal 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
|
||||
```
|
||||
30
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/config.json
Normal file
30
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/config.json
Normal 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
|
||||
}
|
||||
13
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/generation_config.json
Normal file
13
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/generation_config.json
Normal 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"
|
||||
}
|
||||
151388
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/merges.txt
Normal file
151388
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c76fa123a80c02c23b893f5f70b5261371826def47d7141b2c2375eb0923a92d
|
||||
size 1244659944
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44210ebae89ff50ed223b66c48fb5bd3da690983ce3b10cc76289f89b9c2085b
|
||||
size 1082234512
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e54f9d3e91602558c7b53caeb8061dbcb726959a5c9ee30f3e27e99716a50b0
|
||||
size 1082239816
|
||||
@@ -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
BIN
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/tokenizer_config.json
Normal file
239
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/tokenizer_config.json
Normal 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
|
||||
}
|
||||
1
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/vocab.json
Normal file
1
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B/vocab.json
Normal file
File diff suppressed because one or more lines are too long
3
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
Normal file
3
Vikra-HCT-YeAM-3_3.2_QweLLa-1.7B_Q8_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e5c3eab905f68c6f9001d3af2c17c538a1583e6804106d048e0a2b0ca881cd7c
|
||||
size 2165039488
|
||||
3
Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
Normal file
3
Vikra-HCT-YeAM-LLaGemma-1B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:106774be0e59d7939904784f171932c95b759fdbe979948a6df143c966903ea3
|
||||
size 1069306496
|
||||
50
Vikra-HCT-YeAM-LLaGemma-1B/README.md
Normal file
50
Vikra-HCT-YeAM-LLaGemma-1B/README.md
Normal 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
|
||||
```
|
||||
3
Vikra-HCT-YeAM-LLaGemma-1B/added_tokens.json
Normal file
3
Vikra-HCT-YeAM-LLaGemma-1B/added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
37
Vikra-HCT-YeAM-LLaGemma-1B/config.json
Normal file
37
Vikra-HCT-YeAM-LLaGemma-1B/config.json
Normal 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
|
||||
}
|
||||
13
Vikra-HCT-YeAM-LLaGemma-1B/generation_config.json
Normal file
13
Vikra-HCT-YeAM-LLaGemma-1B/generation_config.json
Normal 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"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0d327513594d6e96139c1660d5389b20cc9de3797796b69ca9cb8d21ad420c31
|
||||
size 1081244120
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff4980829a32e0feccf675d107ffc2ebc495139577c3ce7460ffc3a0fe8ff76f
|
||||
size 918566568
|
||||
1
Vikra-HCT-YeAM-LLaGemma-1B/model.safetensors.index.json
Normal file
1
Vikra-HCT-YeAM-LLaGemma-1B/model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
33
Vikra-HCT-YeAM-LLaGemma-1B/special_tokens_map.json
Normal file
33
Vikra-HCT-YeAM-LLaGemma-1B/special_tokens_map.json
Normal 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
|
||||
}
|
||||
}
|
||||
3
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.json
Normal file
3
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.model
Normal file
3
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
51346
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer_config.json
Normal file
51346
Vikra-HCT-YeAM-LLaGemma-1B/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
Normal file
3
Vikra-HCT-YeAM-PhiMma-1B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2cc9a6638b222213cc705401efb8d4ae2aac38bb0c25f4c3315d64be3d6587aa
|
||||
size 1069306496
|
||||
49
Vikra-HCT-YeAM-PhiMma-1B/README.md
Normal file
49
Vikra-HCT-YeAM-PhiMma-1B/README.md
Normal 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
|
||||
```
|
||||
3
Vikra-HCT-YeAM-PhiMma-1B/added_tokens.json
Normal file
3
Vikra-HCT-YeAM-PhiMma-1B/added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
37
Vikra-HCT-YeAM-PhiMma-1B/config.json
Normal file
37
Vikra-HCT-YeAM-PhiMma-1B/config.json
Normal 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
|
||||
}
|
||||
13
Vikra-HCT-YeAM-PhiMma-1B/generation_config.json
Normal file
13
Vikra-HCT-YeAM-PhiMma-1B/generation_config.json
Normal 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"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd10088d6f4ea7bd681d61f3ae77b02e6202587e0817b5d91dad2e949bf248b7
|
||||
size 1081244120
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15d8aa3dfd280419d37ea5b3e79ea12aabf419cf96cbc11b17c8f4c9bb5a4aaa
|
||||
size 918566568
|
||||
1
Vikra-HCT-YeAM-PhiMma-1B/model.safetensors.index.json
Normal file
1
Vikra-HCT-YeAM-PhiMma-1B/model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
33
Vikra-HCT-YeAM-PhiMma-1B/special_tokens_map.json
Normal file
33
Vikra-HCT-YeAM-PhiMma-1B/special_tokens_map.json
Normal 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
|
||||
}
|
||||
}
|
||||
3
Vikra-HCT-YeAM-PhiMma-1B/tokenizer.json
Normal file
3
Vikra-HCT-YeAM-PhiMma-1B/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
Vikra-HCT-YeAM-PhiMma-1B/tokenizer.model
Normal file
3
Vikra-HCT-YeAM-PhiMma-1B/tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
51346
Vikra-HCT-YeAM-PhiMma-1B/tokenizer_config.json
Normal file
51346
Vikra-HCT-YeAM-PhiMma-1B/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf
Normal file
3
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7c4602a441fbf8196b67d81a195f23cd967449f7e8b7451daf92384955c3a8b5
|
||||
size 8727647264
|
||||
51
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/README.md
Normal file
51
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
base_model:
|
||||
- mistralai/Mistral-Nemo-Instruct-2407
|
||||
language:
|
||||
- en
|
||||
- ru
|
||||
---
|
||||
|
||||
# Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B
|
||||
|
||||
HCT architecture release. YeAM (Yet Another Merge) implementation invariant.
|
||||
|
||||
## What it is
|
||||
|
||||
A large (12B-class) checkpoint produced via HCT-compatible merging with 1B Gemma.
|
||||
Published in standard Hugging Face format (safetensors + sharded index) and intended to be convertible to GGUF.
|
||||
|
||||
## 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-Vikhr-NemoGemma-12B_plus_1B"
|
||||
|
||||
tok = AutoTokenizer.from_pretrained(m, use_fast=False)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
m,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto",
|
||||
).eval()
|
||||
|
||||
inputs = tok("Привет!", return_tensors="pt").to(model.device)
|
||||
out = model.generate(**inputs, max_new_tokens=256)
|
||||
print(tok.decode(out[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## GGUF (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
|
||||
CUDA_VISIBLE_DEVICES=0,1 /path/to/llama.cpp/build/bin/llama-server -m model.Q6_K.gguf --n-gpu-layers 99 --split-mode layer --tensor-split 1,1
|
||||
27
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/config.json
Normal file
27
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131074
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.44.2"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed147b1bc8b485b72024ffeee6c75e9ab8dddd822a0e38c99ca61bff2d75f816
|
||||
size 1342197888
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a298abbf07c5711cde1f874e3bfd32b263b16d223fc21821a0745bb5d0226c2a
|
||||
size 1342197904
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6d52f1a2cd0f2fd361e94c133cb1fa71630ce94f4c18ee65f8c23f641407e3ef
|
||||
size 1080076200
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a0cf29e2759bfe4d7a96e195b408e1e0439ae19d402fcbcc600ad19607ff8ac
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:96c0007eab8fdf6546e65d74c497cf41e5877b094e73fc66b99e94f0dacbd50d
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fe0b85cbbb3761cc06fb228e7e254e39d68f40c52a7e0ab4af6cb6685bceace
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d086036870e12cc363b568cc68c0f9cb4a2274ab5647eeba8fa52f4a16ed205b
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e1a2bb26a1fdcc7bdc3d2b4a59732ffcd006ba170117fccd5700c58ad094935
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:22e42950814934bf8c89ef04d010029ea9297c87383ec264cfce598ae00e7059
|
||||
size 1090562096
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e9c1b3aa004516a950fbc1a0dcd2aa4740f69e5b2045c64df7409551d392645
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eefb905db5bbaefb874ba5186a812597c3ae6eac02a72f02a7249c5f78eb17c5
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d99b4d25309fb5359ec484d5288f8a43292929f142d35d958105896c12960818
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b28155a270f86fea50a5548fec83e27ca56f726e82067c083c9687edcb9a4e7
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edc61ac1e876410edf757be8fe7f8b0af3f093b986b73ad0be059224617644c2
|
||||
size 1090562096
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:91c34fb4acc4ac436dd95fa96b8bb6b9c491af2361014eb695da2bfb013c237e
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0fba941e9e6d6eacf945dbbd6d81f68018c25542d2b04add4b864d842ef99946
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f9b81af1b6d443f2b7130983d3b94a5e02daf44dd0e22b5d195833ad0afe502e
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3e478473ed04add3945febdb599c6d46c9e7abe048fcff831281356336ff27a
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:03964a3f635c9dbf39864ca29fc3608c62d4605f1c0e5c6b2c486a5853eefad9
|
||||
size 1090562104
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:83d58e325954a28fb12818d321fc95e65c0fba4539195afec61164dc42b3c3cc
|
||||
size 1090562088
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0354aad9a57376a83cb7e275381c1292deab8babfbadb93969639bd107cb7e1e
|
||||
size 1090562088
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:596611f84d763180d95a36245271e2af2fb9e4ff6f1d307fafd5f5c942a0a107
|
||||
size 1090562088
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ee234d3a8df1dd4c81bed0c5e2a886ca380347c62e4f64451d7ae79a4ee89fd
|
||||
size 10496240
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,202 @@
|
||||
---
|
||||
base_model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.12.0
|
||||
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-05-09-24",
|
||||
"bias": "none",
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 96,
|
||||
"lora_dropout": 0.05,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 96,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"down_proj",
|
||||
"o_proj",
|
||||
"v_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM",
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3e338736bfba1083e8e081c3d6ef857668843049a34d06e9e01bef06f7d57d74
|
||||
size 1368467752
|
||||
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|start_header_id|>",
|
||||
"<|end_header_id|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"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
|
||||
}
|
||||
}
|
||||
409643
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/tokenizer.json
Normal file
409643
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
8039
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/tokenizer_config.json
Normal file
8039
Vikra-HCT-YeAM-Vikhr-NemoGemma-12B_plus_1B/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
Vikra-MixP_4.9b_S.gguf
Normal file
3
Vikra-MixP_4.9b_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:730a94f67e3c4141eabaec7e0cf6235669f2bd1b8743812c919593086efdd109
|
||||
size 9365459776
|
||||
3
Vikra-MixedP-MXFP4.gguf
Normal file
3
Vikra-MixedP-MXFP4.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:76905d2c64820ee9e3067c863a163725e661efdedc8a7929b094d5bd5e9a9dc5
|
||||
size 9006650176
|
||||
Reference in New Issue
Block a user