初始化项目，由ModelHub XC社区提供模型
Model: SicariusSicariiStuff/Sweet_Dreams_12B Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
*.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
|
||||
Images/Sweet_Dreams_12B.png filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
Character_Cards/Adventure/Morrowind_Generic_Mages_Guild.png filter=lfs diff=lfs merge=lfs -text
|
||||
Character_Cards/Roleplay/Ajira_the_Khajiit_alchemist.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/Example_Ajira.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/UGI.png filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:51df8d08a2f9cac4c7b8d3f4280136c58ffc1aea3f07a287dc74514e28ba9bb2
|
||||
size 3191272
|
||||
3
Character_Cards/Roleplay/Ajira_the_Khajiit_alchemist.png
Normal file
3
Character_Cards/Roleplay/Ajira_the_Khajiit_alchemist.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d09b10d26de595a46d446d578c513ec11e4d3c693c17424ff01b089e8892a187
|
||||
size 1299740
|
||||
3
Images/Examples/Example_Ajira.png
Normal file
3
Images/Examples/Example_Ajira.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78371d7d646dfdb80b287b514d87755a54c39b7f8e0bac1c28415001c0a4c25d
|
||||
size 393358
|
||||
3
Images/Sweet_Dreams_12B.png
Normal file
3
Images/Sweet_Dreams_12B.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ff03afc090e9b441a676275c19b707e7540fd89be3a51a248f3736367e1e7d9
|
||||
size 1421498
|
||||
3
Images/UGI.png
Normal file
3
Images/UGI.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:05bcc550e253bad1d5c670ede85588d98d434f1206b5e70cef1dab1f4571f81a
|
||||
size 316487
|
||||
401
README.md
Normal file
401
README.md
Normal file
@@ -0,0 +1,401 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- SicariusSicariiStuff/Impish_Nemo_12B
|
||||
datasets:
|
||||
- SicariusSicariiStuff/UBW_Tapestries
|
||||
widget:
|
||||
- text: "Sweet_Dreams_12B"
|
||||
output:
|
||||
url: https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Images/Sweet_Dreams_12B.png
|
||||
---
|
||||
|
||||
|
||||
<div align="center">
|
||||
<b style="font-size: 40px;">Sweet_Dreams_12B</b>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Images/Sweet_Dreams_12B.png" alt="Sweet_Dreams_12B" style="width: 50%; min-width: 500px; display: block; margin: auto;">
|
||||
|
||||
|
||||
---
|
||||
|
||||
<style>
|
||||
.hf-links, .hf-tldr{
|
||||
display:flex;justify-content:center;align-items:center;flex-wrap:wrap;
|
||||
gap:14px;margin:16px 0;
|
||||
}
|
||||
.hf-links a, .hf-tldr a{
|
||||
display:flex;flex-direction:column;align-items:center;justify-content:center;
|
||||
text-align:center;text-decoration:none;font-weight:700;line-height:1.15;
|
||||
padding:10px 16px;border-radius:14px;border:2px solid currentColor;
|
||||
transition:transform .15s ease,box-shadow .15s ease,background-color .15s ease,color .15s ease;
|
||||
}
|
||||
|
||||
.hf-tldr a{
|
||||
font-size:48px;color:purple;min-width:100%;
|
||||
}
|
||||
.hf-tldr a:hover{
|
||||
transform:translateY(-2px);
|
||||
background:rgba(128,0,128,.1);
|
||||
box-shadow:0 8px 22px rgba(128,0,128,.45);
|
||||
color:#fff;
|
||||
}
|
||||
|
||||
|
||||
.hf-links a{
|
||||
font-size:20px;min-width:240px;max-width:280px;
|
||||
}
|
||||
.hf-links a .top{font-size:16px;opacity:.9;}
|
||||
.hf-links a .bottom{font-size:20px;}
|
||||
|
||||
.hf-links a.red{color:#E31515;}
|
||||
.hf-links a.yellow{color:#FFC800;}
|
||||
.hf-links a.green{color:#64FF00;}
|
||||
|
||||
.hf-links a:hover{
|
||||
transform:translateY(-1px);
|
||||
background:rgba(255,255,255,0.04);
|
||||
box-shadow:0 6px 18px rgba(0,0,0,.15), inset 0 0 0 9999px rgba(255,255,255,.02);
|
||||
}
|
||||
.hf-links a.red:hover{
|
||||
background:rgba(227,21,21,.12);
|
||||
box-shadow:0 8px 20px rgba(227,21,21,.35);
|
||||
color:#fff;
|
||||
}
|
||||
.hf-links a.yellow:hover{
|
||||
background:rgba(255,200,0,.15);
|
||||
box-shadow:0 8px 20px rgba(255,200,0,.35);
|
||||
color:#111;
|
||||
}
|
||||
.hf-links a.green:hover{
|
||||
background:rgba(100,255,0,.14);
|
||||
box-shadow:0 8px 20px rgba(100,255,0,.35);
|
||||
color:#093;
|
||||
}
|
||||
|
||||
/* mobile stacking */
|
||||
@media (max-width:520px){
|
||||
.hf-links a{min-width:100%;max-width:100%;}
|
||||
.hf-tldr a{font-size:36px;}
|
||||
}
|
||||
</style>
|
||||
|
||||
<div class="hf-tldr">
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B#tldr">
|
||||
Click here for TL;DR
|
||||
</a>
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
<div class="hf-links">
|
||||
<a class="red" href="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B#available-quantizations">
|
||||
<span class="top">Click here</span>
|
||||
<span class="bottom">for quantizations</span>
|
||||
</a>
|
||||
|
||||
<a class="yellow" href="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B#recommended-settings-for-assistant-mode">
|
||||
<span class="top">Click here</span>
|
||||
<span class="bottom">for recommended settings</span>
|
||||
</a>
|
||||
|
||||
<a class="green" href="https://ko-fi.com/sicarius">
|
||||
<span class="top">Click here</span>
|
||||
<span class="bottom">to buy me a coffee</span>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
**November 2025**, so many projects, clearly not enough time. The early days of AI are over, and it's **2026** soon. Time flies.
|
||||
|
||||
> Sweet dreams are made of this\
|
||||
Who am I to disagree?
|
||||
|
||||
|
||||
|
||||
**Hippocrates** said:
|
||||
|
||||
> Ars longa, vita brevis!
|
||||
|
||||
Naturally, he was correct.
|
||||
|
||||
---
|
||||
|
||||
This model is focused on making a **strong generalist** for varied **roleplay and adventure** formats. Why do I say generalist? Isn't it a generalist = assistant tasks?
|
||||
|
||||
Usually yes, but here the goal was to be flexible in accepting different styles of character cards and adventure cards, instead of being focused on my **[SICAtxt](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B#sicatxt-for-roleplay)**, hence "generalist".
|
||||
|
||||
While being more flexible to function very well under both common and uncommon formats, I wanted to preserve a quite unique vocabulary usage. *Whispers*, *Echoes*, and *Elara* still exist, but are much, MUCH more rare, and anyone who would spend a couple of minutes with **Sweet_Dreams_12B** will quickly feel its unique vibe. I like it more than I thought I would. There's something very pleasant in its prose and expressiveness.
|
||||
|
||||
Most of my models are intentionally **short-biased** (meaning paragraphs are on the shorter side and fewer). **Not this one.** This model was explicitly made to have a longer form bias, but still with a dynamic paragraph length in mind.
|
||||
|
||||
This model **wasn't abliterated**, and the uncensoring was **gentle** to **preserve as much intelligence as possible**, so for extreme topics, at least in assistant mode, there might be still some rare refusals. I didn't encounter any refusals in roleplay.
|
||||
|
||||
---
|
||||
|
||||
### TL;DR
|
||||
- Accepts **wide range** of character cards formats.
|
||||
- **Unique** vocabulary.
|
||||
- **Very diverse** swipes.
|
||||
- Does adventure well.
|
||||
- **Morrowind** knowledge :)
|
||||
- Feels sometimes **very human** in the way it responds.
|
||||
- **Dynamic length** response with a **slight** bias towards **more paragraphs** (2–5 paragraphs, usually 2–3). Length is adjustable via 1–3 examples in the dialogue. **No more rigid short-bias!**
|
||||
|
||||
---
|
||||
|
||||
# Regarding the format:
|
||||
|
||||
It is **HIGHLY RECOMMENDED** to use the **Roleplay \ Adventure format the model was trained on**, see the examples below for syntax. It allows for a **very fast and easy** writing of character cards with **minimal amount of tokens**. It's a modification of an old-skool CAI style format I call **SICAtxt** (**S**imple, **I**nexpensive **C**haracter **A**ttributes plain-text):
|
||||
|
||||
---
|
||||
|
||||
## **SICAtxt** for **roleplay**:
|
||||
|
||||
```
|
||||
X's Persona: X is a .....
|
||||
Traits:
|
||||
Likes:
|
||||
Dislikes:
|
||||
Quirks:
|
||||
Goals:
|
||||
|
||||
Dialogue example
|
||||
```
|
||||
|
||||
## **SICAtxt** for **Adventure:**
|
||||
|
||||
```
|
||||
Adventure: <short description>
|
||||
$World_Setting:
|
||||
$Scenario:
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Included Character cards in this repo:
|
||||
|
||||
---
|
||||
|
||||
## Roleplay:
|
||||
|
||||
[Ajira - the Khajiit alchemist](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Character_Cards/Roleplay/Ajira_the_Khajiit_alchemist.png) (**Ajira the Khajiit** digging for mushrooms, needs **your help**.)
|
||||
|
||||
## Adventure:
|
||||
|
||||
[Morrowind - Generic Mages Guild](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Character_Cards/Adventure/Morrowind_Generic_Mages_Guild.png) (The **mages guild** is the place to be, how would **you** fare?)
|
||||
|
||||
|
||||
---
|
||||
|
||||
# Other character cards:
|
||||
|
||||
## Adventure:
|
||||
- [Morrowind - Hilde the Nordish Gladiator](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Adventure_Cards/Arena_Fights_Hilde.png) (fighting in the **Arena** in **Vivec**'s city of **Morrowind** for blood and honor.)
|
||||
- [Morrowind - Male Orc](https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B/resolve/main/Adventure_Cards/Adventure_Morrowind_M_Orc.png) (An **Orc** that wants to get to **Balmora** from **Seyda Neen**.)
|
||||
- [Morrowind - Female Breton](https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B/resolve/main/Adventure_Cards/Adventure_Morrowind_F_Breton.png) (A female **Breton** with an impressive... heart, wants to **join the Mages Guild** in **Balmora**.)
|
||||
- [Morrowind - Male Bosmer](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B/resolve/main/Adventure_Cards/Adventure_Morrowind_M_Bosmer.png) (A male **Bosmer** that was just released from prison. Everyone assumes you're a **thief** and a **degenerate**.)
|
||||
- [Morrowind - Male Redguard](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B/resolve/main/Adventure_Cards/Adventure_Morrowind_M_Redguard.png) (A male **Redguard** that tries to get his shit together, and just find a decent job in Morrowind. Everyone are giving you a hard time, and overtly hostile toward you.)
|
||||
|
||||
---
|
||||
|
||||
## Roleplay:
|
||||
- [Calanthe](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Character_Cards/Calanthe_Australian_Prison.png) (The Australian **Overseer** at a rare-earth extraction penal colony, she got **6-pack abs**, but **no mercy**.)
|
||||
- [Alexis](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Character_Cards/Alexis_Survival.png) (The **diabolic reconnaissance officer**, trying to survive the **Safari experience**.)
|
||||
- [Alexandra](https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B/resolve/main/Character_Cards/Alexandra.png) (A networking professional **tsundere** that likes you. She knows **Systema**.)
|
||||
- [Nano_Imp](https://huggingface.co/SicariusSicariiStuff/Nano_Imp_1B/resolve/main/Character_Cards/Nano_Imp.png) (A shrunken palm-sized hellspawn who wants your soul.)
|
||||
- [Shmena Koeset](https://huggingface.co/SicariusSicariiStuff/Fiendish_LLAMA_3B/resolve/main/Character_Cards/Shmena_Koeset.png) (An overweight and foul-mouthed **troll huntress** with a bad temper.)
|
||||
- [Takai_Puraisu](https://huggingface.co/SicariusSicariiStuff/Oni_Mitsubishi_12B/resolve/main/Character_Cards/Takai_Puraisu.png) (Car dealership simulator.)
|
||||
- [Vesper](https://huggingface.co/SicariusSicariiStuff/Phi-Line_14B/resolve/main/Character_Cards/Vesper.png) (Schizo **Space Adventure**.)
|
||||
- [Nina_Nakamura](https://huggingface.co/SicariusSicariiStuff/Phi-Line_14B/resolve/main/Character_Cards/Nina_Nakamura.png) (The **sweetest** dorky co-worker.)
|
||||
- [Employe#11](https://huggingface.co/SicariusSicariiStuff/Phi-Line_14B/resolve/main/Character_Cards/Employee%2311.png) (**Schizo workplace** with a **schizo worker**.)
|
||||
|
||||
---
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
- Intended use: **Role-Play**, **Adventure**, **Creative Writing**, **General Tasks**.
|
||||
|
||||
- Censorship level: <b>Medium - Low</b>
|
||||
|
||||
- **6 / 10** (10 completely uncensored)
|
||||
|
||||
|
||||
## UGI score:
|
||||
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Images/UGI.png" style="width: 100%; min-width: 700px; display: block; margin: auto;">
|
||||
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Available quantizations:
|
||||
|
||||
- Original: [FP16](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B)
|
||||
- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B_GGUF) | [iMatrix-High-Attention](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B_HA_NL)
|
||||
- Specialized: [FP8](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B_FP8)
|
||||
- Mobile (ARM): [Q4_0](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B_ARM) | [Q4_0_High-Attention](https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B_ARM_HA)
|
||||
|
||||
---
|
||||
|
||||
## Recommended settings for assistant mode
|
||||
<details>
|
||||
<summary>Full generation settings: <b>Debug Deterministic</b>.</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow/resolve/main/Presets/Debug-deterministic.png" alt="Debug Deterministic_Settings" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>Full generation settings: <b>min_p</b>.</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow/resolve/main/Presets/min_p.png" alt="min_P_Settings" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
## Recommended settings for Roleplay mode
|
||||
---
|
||||
|
||||
<h2 style="color: green; font-weight: bold; font-size: 36px; text-align: center;">Specialized Roleplay Settings for Sweet_Dreams_12B, click below:</h2>
|
||||
<h2 style="color: chartreuse; font-weight: bold; font-size: 32px; text-align: center;">(Important!)</h2>
|
||||
|
||||
|
||||
|
||||
|
||||
<details>
|
||||
<summary><b>Impish_Magic</b> — Wild, yet very coherent!</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B/resolve/main/Images/Settings/Impish_Magic_Preset.png" alt="Impish_Magic_Preset" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary><b>Fiendish</b> — More wild, but still very coherent!</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Settings/Fiendish_Gen_Settings.png" alt="Fiendish_Preset" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
|
||||
<style>
|
||||
.hf-links{
|
||||
display:flex;justify-content:center;align-items:center;flex-wrap:wrap;
|
||||
gap:14px;margin:16px 0;
|
||||
}
|
||||
.hf-links a{
|
||||
display:flex;flex-direction:column;align-items:center;justify-content:center;
|
||||
text-align:center;text-decoration:none;font-weight:700;line-height:1.15;
|
||||
padding:10px 16px;border-radius:14px;border:2px solid currentColor;
|
||||
transition:transform .15s ease,box-shadow .15s ease,background-color .15s ease,color .15s ease;
|
||||
font-size:20px;min-width:240px;max-width:280px;
|
||||
}
|
||||
.hf-links a .top{font-size:20px;}
|
||||
.hf-links a .bottom{font-size:16px;}
|
||||
|
||||
.hf-links a.red{color:#E31515;}
|
||||
|
||||
.hf-links a:hover{
|
||||
transform:translateY(-1px);
|
||||
background:rgba(255,255,255,0.04);
|
||||
box-shadow:0 6px 18px rgba(0,0,0,.15), inset 0 0 0 9999px rgba(255,255,255,.02);
|
||||
}
|
||||
.hf-links a.red:hover{
|
||||
background:rgba(227,21,21,.12);
|
||||
box-shadow:0 8px 20px rgba(227,21,21,.35);
|
||||
color:#fff;
|
||||
}
|
||||
|
||||
@media (max-width:520px){
|
||||
.hf-links a{min-width:100%;max-width:100%;}
|
||||
}
|
||||
</style>
|
||||
|
||||
<div class="hf-links">
|
||||
<a class="red"
|
||||
href="https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Silly_Tavern_Settings/Impish_Magic_ST.json"
|
||||
target="_blank" rel="noopener" aria-label="Silly Tavern Settings #1 - Click here">
|
||||
<span class="top">Silly Tavern Settings #1 - Click here</span>
|
||||
<span class="bottom">Download JSON</span>
|
||||
</a>
|
||||
|
||||
<a class="red"
|
||||
href="https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Silly_Tavern_Settings/Dynamic_Paragraph_XTC_ST.json"
|
||||
target="_blank" rel="noopener" aria-label="Silly Tavern Settings #2 - Click here">
|
||||
<span class="top">Silly Tavern Settings #2 - Click here</span>
|
||||
<span class="bottom">Download JSON</span>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
- **Silly Tavern Settings #1** - Higher temperature while still being coherent
|
||||
- **Silly Tavern Settings #2** - Dynamic paragraphs, XTC, other stuff
|
||||
|
||||
---
|
||||
|
||||
|
||||
<h2 style="color: lime; font-weight: bold; font-size: 65px; text-align: center;">Chat Examples:</h2>
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B/resolve/main/Images/Examples/Example_Ajira.png" alt="Example_Ajira" style="width: 90%; min-width: 600px; display: block; margin: auto;">
|
||||
|
||||
---
|
||||
|
||||
# Model instruction template: ChatML
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
|
||||
<|im_start|>User request
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>AI answer
|
||||
```
|
||||
|
||||
|
||||
---
|
||||
|
||||
<h2 style="color: green; font-weight: bold; font-size: 65px; text-align: center;">Your support = more models</h2>
|
||||
<a href="https://ko-fi.com/sicarius" style="color: pink; font-weight: bold; font-size: 48px; text-decoration: none; display: block; text-align: center;">My Ko-fi page (Click here)</a>
|
||||
|
||||
---
|
||||
|
||||
|
||||
## Citation Information
|
||||
|
||||
```
|
||||
@llm{Sweet_Dreams_12B,
|
||||
author = {SicariusSicariiStuff},
|
||||
title = {Sweet_Dreams_12B},
|
||||
year = {2025},
|
||||
publisher = {Hugging Face},
|
||||
url = {https://huggingface.co/SicariusSicariiStuff/Sweet_Dreams_12B}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Other stuff
|
||||
- [Impish_LLAMA_4B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B) the **“Impish experience”**, now runnable on spinning rust & toasters.
|
||||
- [Impish_Nemo](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B) A deliciously *impish* Nemo tune.
|
||||
- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
|
||||
- [LLAMA-3_8B_Unaligned](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned) The grand project that started it all.
|
||||
- [Blog and updates (Archived)](https://huggingface.co/SicariusSicariiStuff/Blog_And_Updates) Some updates, some rambles, sort of a mix between a diary and a blog.
|
||||
4
chat_template.jinja
Normal file
4
chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>' + '
|
||||
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||
' }}{% endif %}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "SicariusSicariiStuff/Sweet_Dreams_12B",
|
||||
"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": 131072,
|
||||
"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": "4.53.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.53.2",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26aa10d4325f6eb5a592b244fd79d9406a0d8378b037ea8f356ca1dc29eebfe1
|
||||
size 8976112048
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5d95f671d9ea0d17e4037a85d3f8914dca9765e70d9e91c7a81034a43c1f48d5
|
||||
size 8976155640
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eec95cc1c3f122d9d5ac96fb08cf96a1ad97fac5e9b9ddd6f984bb6941b32c92
|
||||
size 6543339424
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 12247782400,
|
||||
"total_size": 24495564800
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0de30a5895b1aff2e470e085b9898756108ab32944ee156370ad93c2bc373b40
|
||||
size 17078343
|
||||
8015
tokenizer_config.json
Normal file
8015
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user