Guilherme34/Firefly-V3.2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Guilherme34/Firefly-V3.2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-09 20:36:01 +08:00
commit b30c55bad9
12 changed files with 413495 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.gitattributes vendored Normal file
View File

@@ -0,0 +1,39 @@
*.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
copy_91FA56A8-D4E9-457D-BD2C-A011B8D8CD9D.mov filter=lfs diff=lfs merge=lfs -text
IMG_4815.png filter=lfs diff=lfs merge=lfs -text
firefly-v3-logo.png filter=lfs diff=lfs merge=lfs -text
IMG4815.png filter=lfs diff=lfs merge=lfs -text

3
IMG_4815.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f9941c3073e98ec746bf0aceaf8468dccebb351c99be2d98ab563210731a7364
size 5666971

480
README.md Normal file
View File

@@ -0,0 +1,480 @@
---
base_model:
- Guilherme34/Firefly-V2.5
tags:
- merge
- mergekit
- Sakana-ai
- Research-Made-Model
- lazymergekit
- finetuned
- further-trained
- roleplay
- creative-writing
- storytelling
- character-ai
- Guilherme34/Firefly
- SicariusSicariiStuff/Impish_LLAMA_3B
library_name: transformers
---
<div align="center">
<div style="max-width:1040px;margin:0 auto;font-family:Inter,ui-sans-serif,system-ui,-apple-system,BlinkMacSystemFont,'Segoe UI',sans-serif;">
<div style="position:relative;overflow:hidden;background:radial-gradient(circle at 50% 0%,#4a2f68 0%,#172033 45%,#070a12 100%);border:1px solid #3b2f55;border-radius:30px;padding:58px 30px 46px;text-align:center;box-shadow:0 18px 80px rgba(2,6,23,.58);">
<svg width="104" height="104" viewBox="0 0 104 104" fill="none" style="margin-bottom:22px;">
<defs>
<linearGradient id="firefly_v3_gradient" x1="18" y1="10" x2="86" y2="94" gradientUnits="userSpaceOnUse">
<stop stop-color="#C084FC"/>
<stop offset=".45" stop-color="#60A5FA"/>
<stop offset="1" stop-color="#F472B6"/>
</linearGradient>
<radialGradient id="firefly_v3_core" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(52 52) rotate(90) scale(40)">
<stop stop-color="#F5D0FE"/>
<stop offset=".55" stop-color="#60A5FA"/>
<stop offset="1" stop-color="#172033" stop-opacity="0"/>
</radialGradient>
</defs>
<circle cx="52" cy="52" r="42" fill="url(#firefly_v3_core)" opacity=".36">
<animate attributeName="opacity" values=".22;.50;.22" dur="3.8s" repeatCount="indefinite"/>
</circle>
<circle cx="52" cy="52" r="36" stroke="url(#firefly_v3_gradient)" stroke-width="2" opacity=".48">
<animate attributeName="r" values="32;39;32" dur="4.5s" repeatCount="indefinite"/>
<animate attributeName="opacity" values=".26;.62;.26" dur="4.5s" repeatCount="indefinite"/>
</circle>
<path d="M52 17L61.8 39.6L86 43L68.2 59.6L72.6 84L52 71.6L31.4 84L35.8 59.6L18 43L42.2 39.6L52 17Z" stroke="url(#firefly_v3_gradient)" stroke-width="3" stroke-linejoin="round">
<animate attributeName="opacity" values=".72;1;.72" dur="2.6s" repeatCount="indefinite"/>
</path>
</path>
</svg>
<h1 style="margin:0;color:#ffffff;font-size:62px;line-height:1;font-weight:950;letter-spacing:-2px;">
Firefly-V3.2
</h1>
<p style="margin:20px auto 0;max-width:820px;color:#d8d3e7;font-size:19px;line-height:1.8;">
A heavily refined <strong>roleplay-first language model</strong>, built from a novel method(Sakana AI Text to Lora paper)
<strong>additional training</strong>, <strong>EVERYTHING</strong> FROM <strong>Firefly-V3 but Better</strong>.
<a href="https://huggingface.co/mradermacher/Firefly-V3.2-GGUF">(btw if you need the GGUF: https://huggingface.co/mradermacher/Firefly-V3.2-GGUF)</a>
</p>
<p style="margin:14px auto 0;max-width:780px;color:#f0abfc;font-size:16px;line-height:1.7;font-weight:800;">
My personal strongest roleplay model to date now with improvements on roleplay, coherency and math, a literal BRAIN UPGRADE.
</p>
<div style="margin:32px auto 0;display:flex;flex-wrap:wrap;justify-content:center;align-items:center;gap:10px;max-width:940px;">
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#24162e,#111827);border:1px solid #613574;color:#f0abfc;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M21 15a2 2 0 01-2 2H7l-4 4V5a2 2 0 012-2h14a2 2 0 012 2z"/>
<animate attributeName="opacity" values=".65;1;.65" dur="2.6s" repeatCount="indefinite"/>
</svg>
Roleplay
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#1f1b32,#111827);border:1px solid #4f46e5;color:#a5b4fc;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M4 19.5A2.5 2.5 0 016.5 17H20"/>
<path d="M4 4.5A2.5 2.5 0 016.5 2H20v20H6.5A2.5 2.5 0 014 19.5z"/>
<animate attributeName="opacity" values=".6;1;.6" dur="3s" repeatCount="indefinite"/>
</svg>
Storytelling
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#182335,#111827);border:1px solid #315d7a;color:#7dd3fc;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M8 21h8"/>
<path d="M12 17v4"/>
<path d="M7 4h10"/>
<path d="M17 4v5a5 5 0 01-10 0V4"/>
<animateTransform attributeName="transform" type="translate" values="0 0;0 -1;0 0" dur="2s" repeatCount="indefinite"/>
</svg>
Character Acting
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#1c2518,#111827);border:1px solid #315f42;color:#86efac;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M3 12h18"/>
<path d="M3 6h18"/>
<path d="M3 18h18"/>
<animate attributeName="opacity" values=".55;1;.55" dur="2.2s" repeatCount="indefinite"/>
</svg>
Long Chats
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#332117,#111827);border:1px solid #7c4a22;color:#fdba74;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M12 20h9"/>
<path d="M16.5 3.5a2.1 2.1 0 013 3L7 19l-4 1 1-4 12.5-12.5z"/>
<animateTransform attributeName="transform" type="rotate" values="0 12 12;4 12 12;0 12 12;-4 12 12;0 12 12" dur="3s" repeatCount="indefinite"/>
</svg>
Creative Writing
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#171a35,#111827);border:1px solid #3f4a8a;color:#a5b4fc;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M12 2v20"/>
<path d="M5 8h14"/>
<path d="M7 16h10"/>
<animate attributeName="opacity" values=".58;1;.58" dur="2s" repeatCount="indefinite"/>
</svg>
Fine-Tuned + Brain Changing
</span>
<span style="display:inline-flex;align-items:center;gap:8px;background:linear-gradient(180deg,#181c28,#111827);border:1px solid #475569;color:#cbd5e1;padding:10px 17px;border-radius:999px;font-weight:800;box-shadow:inset 0 1px 0 rgba(255,255,255,.05);">
<svg width="17" height="17" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M8 3H5a2 2 0 00-2 2v3"/>
<path d="M16 3h3a2 2 0 012 2v3"/>
<path d="M8 21H5a2 2 0 01-2-2v-3"/>
<path d="M16 21h3a2 2 0 002-2v-3"/>
<path d="M9 9h6v6H9z"/>
<animateTransform attributeName="transform" type="scale" values="1;1.08;1" dur="2.8s" repeatCount="indefinite"/>
</svg>
Merge Foundation
</span>
</div>
</div>
</div>
</div>
---
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/638fd4be2ddd69e70b8cd31c/kYgwK1ZAcFUo1R0djk9EQ.png" alt="Firefly-V3 preview" style="max-width:1040px;width:100%;border-radius:26px;border:1px solid #334155;box-shadow:0 18px 70px rgba(2,6,23,.45);">
</div>
<div align="center">
<video src="https://cdn-uploads.huggingface.co/production/uploads/638fd4be2ddd69e70b8cd31c/DyYIOCFJUqmld1-uw0bts.mp4" controls muted loop style="max-width:1040px;width:100%;border-radius:26px;border:1px solid #334155;box-shadow:0 18px 70px rgba(2,6,23,.45);">
</video>
---
<div style="max-width:1040px;margin:0 auto;font-family:Inter,ui-sans-serif,system-ui,-apple-system,BlinkMacSystemFont,'Segoe UI',sans-serif;">
<div style="background:radial-gradient(circle at top,rgba(96,165,250,.18),transparent 38%),linear-gradient(180deg,#0f172a,#070a12);border:1px solid #334155;border-radius:26px;padding:32px;margin:26px auto;box-shadow:0 16px 60px rgba(2,6,23,.42);">
<h2 style="margin:0 0 14px;color:#ffffff;display:flex;align-items:center;gap:12px;">
<svg width="25" height="25" viewBox="0 0 24 24" fill="none" stroke="#7dd3fc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<circle cx="11" cy="11" r="8"/>
<path d="M21 21l-4.35-4.35"/>
<path d="M8 11h6"/>
<path d="M11 8v6"/>
<animate attributeName="opacity" values=".55;1;.55" dur="2.6s" repeatCount="indefinite"/>
</svg>
J-Lens Observations
</h2>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;max-width:860px;margin:0 0 24px;">
Early visual notes and behavior observations from testing Firefly-V3.2 made with J-Lens.
</p>
<div style="display:grid;grid-template-columns:repeat(auto-fit,minmax(280px,1fr));gap:18px;">
<div style="background:linear-gradient(180deg,#111827,#0b101b);border:1px solid rgba(125,211,252,.28);border-radius:22px;overflow:hidden;box-shadow:0 12px 42px rgba(2,6,23,.34);">
<img src="https://cdn-uploads.huggingface.co/production/uploads/638fd4be2ddd69e70b8cd31c/PrkkQ9dm0Or4diepaDGsG.png" alt="J-Lens observation image 1" style="width:100%;height:auto;display:block;object-fit:contain;background:#020617;">
<div style="padding:20px;">
<h3 style="margin:0 0 10px;color:#7dd3fc;font-size:18px;">Observation 01 — Getting the Right Thing</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;font-size:15px;">
The model can think about the entire response while generating the start of it.
</p>
</div>
</div>
<div style="background:linear-gradient(180deg,#141629,#0b101b);border:1px solid rgba(192,132,252,.30);border-radius:22px;overflow:hidden;box-shadow:0 12px 42px rgba(2,6,23,.34);">
<img src="https://cdn-uploads.huggingface.co/production/uploads/638fd4be2ddd69e70b8cd31c/FvVOQvv5SS5Tgp0m0Wx5-.png" alt="J-Lens observation image 2" style="width:100%;height:auto;display:block;object-fit:contain;background:#020617;">
<div style="padding:20px;">
<h3 style="margin:0 0 10px;color:#c084fc;font-size:18px;">Observation 02 — Thinking Silently</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;font-size:15px;">
The model can focus on things without saying it, for example i asked what is his greatest fear without saying it, and he did.
</p>
</div>
</div>
<div style="background:linear-gradient(180deg,#1b1728,#0b101b);border:1px solid rgba(244,114,182,.30);border-radius:22px;overflow:hidden;box-shadow:0 12px 42px rgba(2,6,23,.34);">
<img src="https://cdn-uploads.huggingface.co/production/uploads/638fd4be2ddd69e70b8cd31c/RboXjNszcvP9s7IbKBcl2.png" alt="J-Lens observation image 3" style="width:100%;height:auto;display:block;object-fit:contain;background:#020617;">
<div style="padding:20px;">
<h3 style="margin:0 0 10px;color:#f472b6;font-size:18px;">Observation 03 — Internal Laugh and Joke</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;font-size:15px;">
The model made a joke to itself and laughed internally.
</p>
</div>
</div>
</div>
</div>
</div>
</div>
---
<div style="max-width:1040px;margin:0 auto;font-family:Inter,ui-sans-serif,system-ui,-apple-system,BlinkMacSystemFont,'Segoe UI',sans-serif;">
<div style="background:linear-gradient(180deg,#101827,#0b101b);border:1px solid #334155;border-radius:24px;padding:30px;margin:26px auto;box-shadow:0 12px 48px rgba(2,6,23,.35);">
<h2 style="margin:0 0 16px;color:#ffffff;display:flex;align-items:center;gap:12px;">
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="#c084fc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M4 19.5A2.5 2.5 0 016.5 17H20"/>
<path d="M4 4.5A2.5 2.5 0 016.5 2H20v20H6.5A2.5 2.5 0 014 19.5z"/>
<animate attributeName="opacity" values=".65;1;.65" dur="3s" repeatCount="indefinite"/>
</svg>
About Firefly-V3
</h2>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
<strong>Firefly-V3</strong> is a heavily refined roleplay model created from a merge foundation and then improved through
additional training, fine-tuning, and roleplay-focused behavioral shaping.
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
The model was built to deliver stronger character presence, more natural dialogue, better scene flow, and more enjoyable
long-form roleplay conversations. The merge is only part of its origin. Firefly-V3's final behavior comes from the extra
training and refinement applied after that foundation.
</p>
<p style="color:#f0abfc;line-height:1.8;font-size:16px;font-weight:800;margin-bottom:0;">
I personally consider Firefly-V3 the best roleplay model I have made so far.
</p>
</svg>
<strong>About Firefly-V3.2</strong>
</h2>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
<strong>Firefly-V3.2</strong> is a model that breaks alot of the concept of making an LLM, its more like finding harmony in Chaos of words.
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
The model was built to do everything V3 could but better!
</p>
<p style="color:#f0abfc;line-height:1.8;font-size:16px;font-weight:800;margin-bottom:0;">
I personally consider Firefly-V3 the best roleplay model I have made so far, but lets see if this is gonna change
</p>
</div>
---
<div style="display:grid;grid-template-columns:repeat(auto-fit,minmax(235px,1fr));gap:16px;margin:26px auto;">
<div style="background:linear-gradient(180deg,#24162e,#0b101b);border:1px solid #613574;border-radius:22px;padding:24px;box-shadow:0 10px 32px rgba(2,6,23,.25);">
<h3 style="margin:0 0 12px;color:#f0abfc;display:flex;align-items:center;gap:10px;">
<svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#f0abfc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M21 15a2 2 0 01-2 2H7l-4 4V5a2 2 0 012-2h14a2 2 0 012 2z"/>
<animate attributeName="opacity" values=".65;1;.65" dur="2.6s" repeatCount="indefinite"/>
</svg>
Roleplay First
</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;">
Designed around immersive character interaction, emotional pacing, scene continuity, and expressive dialogue. - AWARENESS
</p>
</div>
<div style="background:linear-gradient(180deg,#1f1b32,#0b101b);border:1px solid #4f46e5;border-radius:22px;padding:24px;box-shadow:0 10px 32px rgba(2,6,23,.25);">
<h3 style="margin:0 0 12px;color:#a5b4fc;display:flex;align-items:center;gap:10px;">
<svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#a5b4fc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M4 19.5A2.5 2.5 0 016.5 17H20"/>
<path d="M4 4.5A2.5 2.5 0 016.5 2H20v20H6.5A2.5 2.5 0 014 19.5z"/>
<animate attributeName="opacity" values=".6;1;.6" dur="3s" repeatCount="indefinite"/>
</svg>
Further Trained
</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;">
Firefly-V3 was not released as a raw merge. It was further trained and refined to shape its final personality and RP behavior.
</p>
</div>
<div style="background:linear-gradient(180deg,#182335,#0b101b);border:1px solid #315d7a;border-radius:22px;padding:24px;box-shadow:0 10px 32px rgba(2,6,23,.25);">
<h3 style="margin:0 0 12px;color:#7dd3fc;display:flex;align-items:center;gap:10px;">
<svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#7dd3fc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M8 21h8"/>
<path d="M12 17v4"/>
<path d="M7 4h10"/>
<path d="M17 4v5a5 5 0 01-10 0V4"/>
<animateTransform attributeName="transform" type="translate" values="0 0;0 -1;0 0" dur="2s" repeatCount="indefinite"/>
</svg>
Character Presence
</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;">
Built to make characters feel more distinct, expressive, and consistent across longer chats.
</p>
</div>
<div style="background:linear-gradient(180deg,#332117,#0b101b);border:1px solid #7c4a22;border-radius:22px;padding:24px;box-shadow:0 10px 32px rgba(2,6,23,.25);">
<h3 style="margin:0 0 12px;color:#fdba74;display:flex;align-items:center;gap:10px;">
<svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="#fdba74" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M12 20h9"/>
<path d="M16.5 3.5a2.1 2.1 0 013 3L7 19l-4 1 1-4 12.5-12.5z"/>
<animateTransform attributeName="transform" type="rotate" values="0 12 12;4 12 12;0 12 12;-4 12 12;0 12 12" dur="3s" repeatCount="indefinite"/>
</svg>
Creative Writing
</h3>
<p style="margin:0;color:#cbd5e1;line-height:1.75;">
Strong for prose, atmosphere, dialogue, character descriptions, and interactive fiction.
</p>
</div>
</div>
---
<div style="background:radial-gradient(circle at top left,rgba(192,132,252,.18),transparent 36%),linear-gradient(135deg,#141b2b,#1e293b);border:1px solid #475569;border-radius:26px;padding:32px;margin:26px auto;box-shadow:0 16px 60px rgba(2,6,23,.38);">
<h2 style="margin:0 0 16px;color:#ffffff;display:flex;align-items:center;gap:12px;">
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="#f0abfc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M12 20h9"/>
<path d="M16.5 3.5a2.1 2.1 0 013 3L7 19l-4 1 1-4 12.5-12.5z"/>
<animate attributeName="opacity" values=".58;1;.58" dur="2.4s" repeatCount="indefinite"/>
</svg>
Best For
</h2>
<div style="display:grid;grid-template-columns:repeat(auto-fit,minmax(220px,1fr));gap:12px;">
<div style="background:rgba(15,23,42,.72);border:1px solid rgba(148,163,184,.22);border-radius:18px;padding:16px;">
<div style="color:#ffffff;font-weight:900;">Roleplay chats</div>
<div style="color:#94a3b8;line-height:1.6;margin-top:5px;">Character-driven conversations and interactive scenes.</div>
</div>
<div style="background:rgba(15,23,42,.72);border:1px solid rgba(148,163,184,.22);border-radius:18px;padding:16px;">
<div style="color:#ffffff;font-weight:900;">Character cards</div>
<div style="color:#94a3b8;line-height:1.6;margin-top:5px;">Bots with personality, style, and scene memory.</div>
</div>
<div style="background:rgba(15,23,42,.72);border:1px solid rgba(148,163,184,.22);border-radius:18px;padding:16px;">
<div style="color:#ffffff;font-weight:900;">Creative writing</div>
<div style="color:#94a3b8;line-height:1.6;margin-top:5px;">Narration, dialogue, atmosphere, and prose.</div>
</div>
<div style="background:rgba(15,23,42,.72);border:1px solid rgba(148,163,184,.22);border-radius:18px;padding:16px;">
<div style="color:#ffffff;font-weight:900;">Long scenes</div>
<div style="color:#94a3b8;line-height:1.6;margin-top:5px;">Extended interactions that need pacing and continuity.</div>
</div>
</div>
</div>
---
<div style="background:linear-gradient(180deg,#101827,#0b101b);border-left:5px solid #c084fc;border-radius:0 22px 22px 0;padding:28px;margin:26px auto;box-shadow:0 12px 48px rgba(2,6,23,.32);">
<h2 style="margin:0 0 16px;color:#ffffff;display:flex;align-items:center;gap:12px;">
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="#c084fc" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<path d="M8 3H5a2 2 0 00-2 2v3"/>
<path d="M16 3h3a2 2 0 012 2v3"/>
<path d="M8 21H5a2 2 0 01-2-2v-3"/>
<path d="M16 21h3a2 2 0 002-2v-3"/>
<path d="M9 9h6v6H9z"/>
<animateTransform attributeName="transform" type="scale" values="1;1.08;1" dur="2.8s" repeatCount="indefinite"/>
</svg>
Training and Model Lineage
</h2>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
Firefly-V3 began from <strong>Guilherme34/Firefly-V2.5</strong> and merge components including
<strong>SicariusSicariiStuff/Impish_LLAMA_3B</strong>, but it did not stop there.
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
After the merge foundation, the model went through additional training and fine-tuning to improve roleplay behavior,
character voice, response style, dialogue quality, and long-form scene handling.
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;margin-bottom:0;">
Then a method called Text-to-Lora was used for making it more creative, coherent and <strong>AWARE</strong> making now Firefly-V3.2
</p>
</div>
---
<div style="background:linear-gradient(180deg,#101827,#0b101b);border:1px solid #334155;border-radius:24px;padding:28px;margin:26px auto;box-shadow:0 12px 48px rgba(2,6,23,.32);">
<h2 style="margin:0 0 16px;color:#ffffff;display:flex;align-items:center;gap:12px;">
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="#60a5fa" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
<circle cx="12" cy="8" r="5"/>
<path d="M20 21a8 8 0 00-16 0"/>
<animate attributeName="opacity" values=".62;1;.62" dur="3s" repeatCount="indefinite"/>
</svg>
Attribution
</h2>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
<strong>Model:</strong> Firefly-V3<br>
<strong>Author:</strong> Guilherme34
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;">
<strong>Base:</strong> Guilherme34/Firefly-V2.5<br>
<strong>Merge Component:</strong> SicariusSicariiStuff/Impish_LLAMA_3B
</p>
<p style="color:#cbd5e1;line-height:1.8;font-size:16px;margin-bottom:0;">
This model is part of the Firefly family and was further trained and refined for users who want a stronger,
more immersive roleplay experience.
</p>
</div>
<div style="background: #111118; border-left: 3px solid #ff4500; border-radius: 0 12px 12px 0; padding: 20px 24px; margin-bottom: 24px;">
<strong>⚠️ Disclaimer</strong>
<p style="color: #8888a0; font-size: 14px; margin: 8px 0 0 0;">This model is <strong>uncensored</strong> and will generate content without built-in refusals. It is intended for <strong>creative fiction and roleplay between consenting adults.</strong> The creator is not responsible for how the model is used. Do not use it to produce content that is illegal in your jurisdiction.</p>
</div>
---
<div align="center">
<div style="background:radial-gradient(circle at 50% 0%,rgba(192,132,252,.24),transparent 40%),linear-gradient(135deg,#080b12,#111827 62%,#172033);border:1px solid #334155;border-radius:28px;padding:36px 28px;margin:26px auto 0;text-align:center;box-shadow:0 18px 70px rgba(2,6,23,.44);">
<svg width="54" height="54" viewBox="0 0 54 54" fill="none" style="margin-bottom:14px;">
<defs>
<linearGradient id="firefly_v3_footer" x1="8" y1="6" x2="46" y2="48" gradientUnits="userSpaceOnUse">
<stop stop-color="#C084FC"/>
<stop offset=".55" stop-color="#60A5FA"/>
<stop offset="1" stop-color="#F472B6"/>
</linearGradient>
</defs>
<circle cx="27" cy="27" r="20" stroke="url(#firefly_v3_footer)" stroke-width="2" opacity=".35">
<animate attributeName="r" values="17;22;17" dur="3s" repeatCount="indefinite"/>
<animate attributeName="opacity" values=".2;.55;.2" dur="3s" repeatCount="indefinite"/>
</circle>
<path d="M27 8L32 20L45 22L35.5 31L38 44L27 37L16 44L18.5 31L9 22L22 20L27 8Z" stroke="url(#firefly_v3_footer)" stroke-width="2.3" stroke-linejoin="round">
<animate attributeName="opacity" values=".7;1;.7" dur="2.4s" repeatCount="indefinite"/>
</path>
</svg>
<h3 style="color:#ffffff;margin:0;font-size:24px;">
Firefly-V3.2
</h3>
<p style="color:#cbd5e1;line-height:1.8;max-width:720px;margin:14px auto 0;font-size:16px;">
A further-improved Firefly-V3 for people who really enjoyed it!
</p>
</div>
</div>
</div>

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"dtype": "bfloat16",
"eos_token_id": 128009,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"transformers_version": "4.57.1",
"use_cache": false,
"vocab_size": 128256
}

3
copy_91FA56A8-D4E9-457D-BD2C-A011B8D8CD9D.mov Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd4b48e199b3597092d149d1a882f8c3b8b1ab156c04de64e1a9b11fd4ca5658
size 19682987

18
mergekit_config.yml Normal file
View File

@@ -0,0 +1,18 @@
models:
- model: Guilherme34/Firefly
parameters:
weight: 1.0
- model: SicariusSicariiStuff/Impish_LLAMA_3B
parameters:
weight: 0.2
merge_method: task_arithmetic
base_model: Guilherme34/Firefly
dtype: bfloat16
parameters:
normalize: true
int8_mask: true

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9256da7668712839d613710a2b5847f5863c5d2bdb68fcdd499a029c621c7df
size 4990977384

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:910c1ac36af4d82ef58ddca565211aafd6815e62b4d48cc7bc4df4cdc803d1e5
size 1434551664

262
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,262 @@
{
"metadata": {
"total_size": 6425499648,
"mergekit_version": "0.1.4"
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors"
}
}

23
special_tokens_map.json Normal file
View File

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

410563
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2063
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff