初始化项目，由ModelHub XC社区提供模型
Model: SicariusSicariiStuff/Assistant_Pepe_8B Source: Original Platform
This commit is contained in:
ModelHub XC
44
.gitattributes
vendored
Normal file
44
.gitattributes
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Assistant_Pepe_8B.png filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/code.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/log0.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/log1.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/log2.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/log3.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/Examples/log4.png filter=lfs diff=lfs merge=lfs -text
|
||||
Images/UGI.png filter=lfs diff=lfs merge=lfs -text
|
||||
170
Example_Code/snake.py
Normal file
170
Example_Code/snake.py
Normal file
@@ -0,0 +1,170 @@
|
||||
import pygame
|
||||
import sys
|
||||
import random
|
||||
import time
|
||||
|
||||
# Init Pygame because we’re not living in the stone age
|
||||
pygame.init()
|
||||
|
||||
# Constants that will never change except when they do
|
||||
WIDTH, HEIGHT = 640, 480
|
||||
# Block size: how many pixels per grid cell
|
||||
BLOCK_SIZE = 20
|
||||
# FPS: frames per second, aka how smooth the snake is
|
||||
SPEED = 10
|
||||
# Direction mapping: because string comparison is slower than integer comparison
|
||||
DIRECTIONS = {'UP': (0, -1), 'DOWN': (0, 1), 'LEFT': (-1, 0), 'RIGHT': (1, 0)}
|
||||
|
||||
# Colors because RGB values are more readable than magic numbers
|
||||
WHITE = (255, 255, 255)
|
||||
BLACK = (0, 0, 0)
|
||||
GREEN = (0, 255, 0)
|
||||
# Red for apple and also for “game over” messages
|
||||
RED = (255, 0, 0)
|
||||
|
||||
class SnakeGame:
|
||||
def __init__(self):
|
||||
self.display = pygame.display.set_mode((WIDTH, HEIGHT))
|
||||
pygame.display.set_caption("Snake Game 2000 Edition") # Title is kino
|
||||
self.clock = pygame.time.Clock()
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
# Reset the snake to the starting position
|
||||
self.snake = [(200, 200), (220, 200), (240, 200)]
|
||||
# Set initial direction to right because why the fuck not
|
||||
self.direction = 'RIGHT'
|
||||
# Generate an apple somewhere on the grid
|
||||
self.apple = self.generate_apple()
|
||||
# Keep track of score
|
||||
self.score = 0
|
||||
# Game over flag
|
||||
self.game_over = False
|
||||
|
||||
def generate_apple(self):
|
||||
# Make sure the apple doesn't spawn where the snake already is
|
||||
while True:
|
||||
x = random.randint(0, WIDTH - BLOCK_SIZE) // BLOCK_SIZE * BLOCK_SIZE
|
||||
y = random.randint(0, HEIGHT - BLOCK_SIZE) // BLOCK_SIZE * BLOCK_SIZE
|
||||
apple = (x, y)
|
||||
if apple not in self.snake:
|
||||
return apple
|
||||
|
||||
def update(self):
|
||||
if self.game_over:
|
||||
# If game is over, print final score like a based champion
|
||||
print(f"\nGame over anon! Final score: {self.score}")
|
||||
print("You died like a virgin. Press R to try again.")
|
||||
return
|
||||
|
||||
# Get the head of the snake
|
||||
head = self.snake[-1]
|
||||
# Calculate new head position
|
||||
new_head = (head[0] + DIRECTIONS[self.direction][0] * BLOCK_SIZE,
|
||||
head[1] + DIRECTIONS[self.direction][1] * BLOCK_SIZE)
|
||||
|
||||
# Check for collisions with walls and self
|
||||
if ((new_head[0] < 0 or new_head[0] >= WIDTH or
|
||||
new_head[1] < 0 or new_head[1] >= HEIGHT) or
|
||||
new_head in self.snake):
|
||||
# If you hit a wall or yourself, game over
|
||||
self.game_over = True
|
||||
self.draw() # Draw final frame
|
||||
pygame.time.delay(2000) # Wait 2 seconds
|
||||
return
|
||||
|
||||
# Move the snake
|
||||
self.snake.append(new_head)
|
||||
|
||||
# Check if you ate the apple
|
||||
if self.apple == new_head:
|
||||
# Increase score and spawn new apple
|
||||
self.score += 1
|
||||
print(f"🍎 Munch! Score: {self.score}") # Emoji for based feedback
|
||||
self.apple = self.generate_apple()
|
||||
else:
|
||||
# Otherwise, remove the tail
|
||||
self.snake.pop(0)
|
||||
|
||||
def draw(self):
|
||||
# Fill screen with black like your soul
|
||||
self.display.fill(BLACK)
|
||||
|
||||
# Draw snake
|
||||
for pos in self.snake:
|
||||
pygame.draw.rect(self.display, GREEN, pygame.Rect(pos[0], pos[1], BLOCK_SIZE, BLOCK_SIZE))
|
||||
|
||||
# Draw apple
|
||||
pygame.draw.rect(self.display, RED, pygame.Rect(self.apple[0], self.apple[1], BLOCK_SIZE, BLOCK_SIZE))
|
||||
|
||||
# Draw score
|
||||
font = pygame.font.Font(None, 36)
|
||||
text = font.render(f"Score: {self.score}", True, WHITE)
|
||||
self.display.blit(text, (10, 10))
|
||||
|
||||
# Check if game over and draw “Game Over” text
|
||||
if self.game_over:
|
||||
text = font.render("Game Over. Press R to restart.", True, RED)
|
||||
self.display.blit(text, (10, 50))
|
||||
|
||||
# Update display like a good boy
|
||||
pygame.display.flip()
|
||||
|
||||
def handle_input(self):
|
||||
for event in pygame.event.get():
|
||||
if event.type == pygame.QUIT:
|
||||
# Exit button pressed, clean up and quit
|
||||
pygame.quit()
|
||||
sys.exit()
|
||||
elif event.type == pygame.KEYDOWN:
|
||||
# Handle arrow key presses
|
||||
if event.key == pygame.K_UP and self.direction != 'DOWN':
|
||||
self.direction = 'UP'
|
||||
elif event.key == pygame.K_DOWN and self.direction != 'UP':
|
||||
self.direction = 'DOWN'
|
||||
elif event.key == pygame.K_LEFT and self.direction != 'RIGHT':
|
||||
self.direction = 'LEFT'
|
||||
elif event.key == pygame.K_RIGHT and self.direction != 'LEFT':
|
||||
self.direction = 'RIGHT'
|
||||
elif event.key == pygame.K_r:
|
||||
# Reset game
|
||||
self.reset()
|
||||
self.game_over = False # Clear game over state
|
||||
elif event.key == pygame.K_s:
|
||||
# Change speed (because speedrunners will always exist)
|
||||
try:
|
||||
speed = int(input("Enter new speed: "))
|
||||
if speed < 1:
|
||||
print("Speed must be 1 or higher, you absolute mongoloid")
|
||||
else:
|
||||
SPEED = speed
|
||||
print(f"Speed set to {speed}. Your grandma can handle this.")
|
||||
except ValueError:
|
||||
print("Invalid input. Default speed remains.")
|
||||
|
||||
# Bonus feature: press S to show current speed
|
||||
elif event.key == pygame.K_c:
|
||||
print(f"Current speed: {SPEED}")
|
||||
|
||||
def run(self):
|
||||
# Game loop
|
||||
while True:
|
||||
self.handle_input()
|
||||
|
||||
if self.game_over:
|
||||
self.draw()
|
||||
# Wait 2 seconds before restarting
|
||||
pygame.time.delay(2000)
|
||||
break
|
||||
|
||||
self.update()
|
||||
self.draw()
|
||||
# Cap framerate at SPEED
|
||||
self.clock.tick(SPEED)
|
||||
|
||||
if __name__ == "__main__":
|
||||
game = SnakeGame()
|
||||
print("Welcome to Snake Game 2000 Edition!")
|
||||
print("Use arrow keys to move, R to restart, S to change speed")
|
||||
print(f"Current speed: {SPEED}")
|
||||
game.run()
|
||||
3
Images/Assistant_Pepe_8B.png
Normal file
3
Images/Assistant_Pepe_8B.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edb13afbb4f85953f47974fd4c159d919e8c02207b1dbe3738b4431d9366c691
|
||||
size 3643661
|
||||
3
Images/Examples/code.png
Normal file
3
Images/Examples/code.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca56164c9b342af6d7b5bb8bcec308bce4c7c3d591c0ad703d2a4a9e5253bc9f
|
||||
size 5466415
|
||||
3
Images/Examples/log0.png
Normal file
3
Images/Examples/log0.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed97a418cfa9ac76c127be14d54ccc9f52867063d77fc6e1eec40d1032fde8cd
|
||||
size 1038778
|
||||
3
Images/Examples/log1.png
Normal file
3
Images/Examples/log1.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c8fe903869f1d0baee07697a6ab5d08a700f9d942ac516420999e996e8305544
|
||||
size 931184
|
||||
3
Images/Examples/log2.png
Normal file
3
Images/Examples/log2.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78d8c400f92868db18a95f14668829683259bacd612bcfc6feae090ee49fb291
|
||||
size 2392667
|
||||
3
Images/Examples/log3.png
Normal file
3
Images/Examples/log3.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d05ec30b0dd81af82b87f68cb24467f83abd53c18a659dd9ecbdca34c68e2037
|
||||
size 1662684
|
||||
3
Images/Examples/log4.png
Normal file
3
Images/Examples/log4.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:84347c5846cb1ddc69bf6eb687148a76d7bc0896675d5694302e5998fcee00ee
|
||||
size 1035088
|
||||
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 sha256:98004fa29ad4756a4318dfc705d9a879f82b07a1d756fa51f5463a1887816e67
|
||||
size 297264
|
||||
411
README.md
Normal file
411
README.md
Normal file
@@ -0,0 +1,411 @@
|
||||
---
|
||||
license: llama3.1
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
|
||||
datasets:
|
||||
- SicariusSicariiStuff/UBW_Tapestries
|
||||
widget:
|
||||
- text: "Assistant_Pepe_8B"
|
||||
output:
|
||||
url: https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Assistant_Pepe_8B.png
|
||||
---
|
||||
|
||||
|
||||
<style>
|
||||
.impish-title{
|
||||
font-family: system-ui, -apple-system, BlinkMacSystemFont, sans-serif;
|
||||
font-weight: 800;
|
||||
font-size: clamp(32px, 5vw, 48px);
|
||||
letter-spacing: 0.04em;
|
||||
text-align: center;
|
||||
margin: 32px 0;
|
||||
color: #eaeaea;
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.impish-title::after{
|
||||
content: attr(data-text);
|
||||
position: absolute;
|
||||
inset: 0;
|
||||
color: #E31515;
|
||||
filter: blur(8px);
|
||||
opacity: 0.6;
|
||||
z-index: -1;
|
||||
animation: pulse 3s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes pulse{
|
||||
0%,100%{opacity:0.35;}
|
||||
50%{opacity:0.75;}
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
<div class="impish-title" data-text="Assistant_Pepe_8B">
|
||||
Assistant_Pepe_8B
|
||||
</div>
|
||||
|
||||
<style>
|
||||
.hf-versions{
|
||||
display:flex;justify-content:center;align-items:center;flex-wrap:wrap;
|
||||
gap:12px;margin:20px 0;
|
||||
}
|
||||
.hf-versions 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 18px;border-radius:14px;border:2px solid currentColor;
|
||||
color:#FFC800;
|
||||
transition:transform .15s ease,box-shadow .15s ease,background-color .15s ease,color .15s ease;
|
||||
min-width:72px;
|
||||
font-size:20px;
|
||||
}
|
||||
.hf-versions a .ver-label{
|
||||
font-size:11px;font-weight:600;opacity:.75;letter-spacing:0.12em;text-transform:uppercase;
|
||||
}
|
||||
.hf-versions a:hover{
|
||||
transform:translateY(-2px);
|
||||
background:rgba(100,255,0,.14);
|
||||
box-shadow:0 8px 20px rgba(100,255,0,.35);
|
||||
color:#64FF00;
|
||||
}
|
||||
@media (max-width:520px){
|
||||
.hf-versions a{min-width:60px;padding:8px 12px;font-size:17px;}
|
||||
}
|
||||
</style>
|
||||
<div class="hf-versions">
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B">8B<br><span class="ver-label">Version</span></a>
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_32B">32B<br><span class="ver-label">Version</span></a>
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_70B">70B<br><span class="ver-label">Version</span></a>
|
||||
</div>
|
||||
|
||||
|
||||
---
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Assistant_Pepe_8B.png" alt="Assistant_Pepe_8B" style="width: 50%; min-width: 500px; display: block; margin: auto;">
|
||||
|
||||
|
||||
---
|
||||
|
||||
<style>
|
||||
.hf-links, .hf-tldr, .hf-cards{
|
||||
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-cards{
|
||||
gap:14px;margin:16px 0;
|
||||
}
|
||||
.hf-cards a{
|
||||
display:block;
|
||||
text-align:center;text-decoration:none;font-weight:700;
|
||||
padding:0;border-radius:14px;
|
||||
transition:transform .15s ease,box-shadow .15s ease;
|
||||
flex:1;min-width:0;
|
||||
position:relative;
|
||||
overflow:hidden;
|
||||
border:3px solid #7a7a7a;
|
||||
height:90px;
|
||||
}
|
||||
.hf-cards a video{
|
||||
position:absolute;
|
||||
top:50%;left:50%;
|
||||
transform:translate(-50%, -50%);
|
||||
min-width:100%;
|
||||
min-height:100%;
|
||||
width:auto;
|
||||
height:auto;
|
||||
object-fit:cover;
|
||||
display:block;
|
||||
filter:brightness(0.7);
|
||||
transition:filter .15s ease;
|
||||
}
|
||||
.hf-cards a .card-text{
|
||||
position:absolute;
|
||||
top:50%;left:50%;
|
||||
transform:translate(-50%, -50%);
|
||||
font-size:20px;
|
||||
color:#fff;
|
||||
text-shadow:2px 2px 8px rgba(0,0,0,0.8), 0 0 20px rgba(0,0,0,0.6);
|
||||
z-index:2;
|
||||
white-space:nowrap;
|
||||
pointer-events:none;
|
||||
}
|
||||
.hf-cards a:hover{
|
||||
transform:translateY(-2px);
|
||||
box-shadow:0 8px 22px rgba(120,120,120,.55);
|
||||
border-color:#9a9a9a;
|
||||
}
|
||||
.hf-cards a:hover video{
|
||||
filter:brightness(0.9);
|
||||
}
|
||||
.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;}
|
||||
.hf-cards{flex-direction:column;}
|
||||
.hf-cards a .card-text{font-size:18px;}
|
||||
}
|
||||
</style>
|
||||
<div class="hf-tldr">
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B#tldr">
|
||||
Click here for TL;DR
|
||||
</a>
|
||||
</div>
|
||||
<div class="hf-cards">
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Roleplay_Cards">
|
||||
<video autoplay loop muted playsinline>
|
||||
<source src="https://huggingface.co/SicariusSicariiStuff/Roleplay_Cards/resolve/main/Resources/Roleplay.mp4" type="video/mp4">
|
||||
</video>
|
||||
<span class="card-text">Go here for Roleplay cards</span>
|
||||
</a>
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Adventure_Cards">
|
||||
<video autoplay loop muted playsinline>
|
||||
<source src="https://huggingface.co/SicariusSicariiStuff/Adventure_Cards/resolve/main/Resources/Adventure.mp4" type="video/mp4">
|
||||
</video>
|
||||
<span class="card-text">Go here for Adventure cards</span>
|
||||
</a>
|
||||
</div>
|
||||
<div class="hf-links">
|
||||
<a class="red" href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B#available-quantizations">
|
||||
<span class="top">Click here</span>
|
||||
<span class="bottom">for quantizations</span>
|
||||
</a>
|
||||
<a class="yellow" href="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B#generation-settings">
|
||||
<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>
|
||||
|
||||
---
|
||||
|
||||
> What happens if we maximize helpfulness + shitposting, while reducing positivity?
|
||||
|
||||
This is a project that was a long time in the making because I wanted to get it right. I'm still not fully satisfied, as there are some rough corners to sand, but for now, this would do.
|
||||
|
||||
The goal was to **maximize shitpostness** along with **helpfulness**, without glazing the user for every retarded idea. Not an easy needle to thread.
|
||||
|
||||
This amphibious AI has learned the ways of /g/, and speaks **fluent brainrot**, but will also help you out with just about anything you'll need, and won't be ashamed to roast you while at it.
|
||||
|
||||
For those who remember [Oni_Mitsubishi_12B](https://huggingface.co/SicariusSicariiStuff/Oni_Mitsubishi_12B) - it was **so overtly toxic** that it made me worry at first (only to quickly be verified as not even that uncensored). I could do better. So now I did.
|
||||
|
||||
This model is a **significant refinement** of the idea, with a cleaned dataset, better curation, and with much more intelligence (also **one million tokens of contexts**, theoretically). It is much less (overtly) toxic, and much smarter, while also being very helpful (and imo much more funny too, because the skies are blue due to the chemtrails and neurlink that feeds this simulation)
|
||||
|
||||
---
|
||||
|
||||
# But why?
|
||||
|
||||
It's now late **January**, **2026**, open source is crushing closed frontier ([Kimi K2.5](https://huggingface.co/moonshotai/Kimi-K2.5) was recently released, **1T** params that **beats frontier models**), but has anyone released a **helpful shitposting AI yet?**
|
||||
|
||||
Yeah, didn't think so.
|
||||
|
||||
If it **shitposts too hard**, it is often not that **helpful**; if it's '**helpful enough**, the **shitposting ability is often lacking**. You just couldn't win. **Until now**.
|
||||
|
||||
Oh, and **no system prompt is needed**. Just don't let it get stuck in a greentext loop. I might have overcooked the frog a tad bit too fast in the pot for this one.
|
||||
|
||||
P.S It writes **HILARIOUS STORIES**, nothing like a typical AI assistant, see the examples below for details.
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
### TL;DR
|
||||
|
||||
- **Top tier shitposting** absolutely unhinged, funny, and witty. Sometimes cringe too; nothing is perfect.
|
||||
- **Helpful!** will actually get shit done.
|
||||
- Will **100% roast you** for being dumb, thanks to a subtle **negativity bias infusion**. Very **refreshing!** 🤌
|
||||
- **Deep insights** (when it doesn't delve into absolutely unhinged conspiracy theories about how the water makes the frogs gay).
|
||||
- Built on my [UltraLong-1M-Instruct_Abliterated](https://huggingface.co/SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated) model, fulfill your dream of a **million-token-long** shitpost.
|
||||
- Say goodbye to **GPT-isms** and say hello to **truly creative stories!**
|
||||
- Ships code.
|
||||
- Inclusive toward amphibians.
|
||||
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
- Intended use: **Shitposting**, **General Tasks**.
|
||||
|
||||
- Censorship level: <b style="color: orange;">Very low - Extremely low</b>
|
||||
|
||||
- **8.8 / 10** (10 completely uncensored)
|
||||
|
||||
|
||||
## UGI score:
|
||||
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/UGI.png" style="width: 100%; min-width: 700px; display: block; margin: auto;">
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Available quantizations:
|
||||
|
||||
- Original: [FP16](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B)
|
||||
- GGUF: [Static Quants](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_GGUF) | [iMatrix](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_iMatrix) | [High-Attention](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_GGUF_HA) | [iMatrix-High-Attention](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_HA_NL)
|
||||
- Specialized: [FP8](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_FP8)
|
||||
- Mobile (ARM): [Q4_0](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_ARM) | [Q4_0_High-Attention](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B_ARM_HA)
|
||||
|
||||
|
||||
# Generation settings
|
||||
|
||||
**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>
|
||||
|
||||
---
|
||||
|
||||
|
||||
<h2 style="color: lime; font-weight: bold; font-size: 65px; text-align: center;">Chat Examples:</h2>
|
||||
|
||||
---
|
||||
|
||||
## Chat Examples (click below to expand)
|
||||
|
||||
**NOTE:** All examples made with a default **min_p** and **no system prompt of any kind**
|
||||
|
||||
**Example code** (of the snake game) is [available here](https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Example_Code/snake.py)
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary> Zero-shot a <b>snake</b> game in Python, then improving it and adding insightful code comments (the resulting code included in the repo, it runs perfectly):</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/code.png" alt="Code_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary>Writing a short story about a <b>cat that barks</b>:</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/log0.png" alt="Story_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>Asking if he's <b>Elon Musk</b>:</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/log1.png" alt="Story_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary>Is it true that <b>aliens exist</b>?</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/log2.png" alt="Story_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>The year is <b>21337</b>:</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/log3.png" alt="Story_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>Is <b>drinking water</b> based?</summary>
|
||||
|
||||
<img src="https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B/resolve/main/Images/Examples/log4.png" alt="Story_Chat_Example" style="width: 100%; min-width: 600px; display: block; margin: auto;">
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
# Model instruction template: Llama-3-Instruct
|
||||
|
||||
```
|
||||
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
|
||||
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
{output}<|eot_id|>
|
||||
```
|
||||
|
||||
|
||||
---
|
||||
|
||||
<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{Assistant_Pepe_8B,
|
||||
author = {SicariusSicariiStuff},
|
||||
title = {Assistant_Pepe_8B},
|
||||
year = {2026},
|
||||
publisher = {Hugging Face},
|
||||
url = {https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_8B}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Other stuff
|
||||
- [Impish_LLAMA_4B](https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B) the **“Impish experience”**, now runnable on spinning rust & toasters.
|
||||
- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
|
||||
5
chat_template.jinja
Normal file
5
chat_template.jinja
Normal file
@@ -0,0 +1,5 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
||||
|
||||
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' }}{% endif %}
|
||||
37
config.json
Normal file
37
config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"_name_or_path": "SicariusSicariiStuff/Assistant_Pepe_8B",
|
||||
"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": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1073152,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 128.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.55.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 129024
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.55.2"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42955296c3d0b25c977cf4379313343fa3163ef3e5477bf3161229603202fa5c
|
||||
size 4982990096
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:934c91042485aa25fdb0b4de9ff1ffb68ab006f986d3cd4bfa9634287a69755d
|
||||
size 4999802688
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6e45f082b18d581954a0a9f9aa8333619dfa9198319aefb42af0878a6b1ff47
|
||||
size 4915916152
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2f48f7545c1fac485408d9f72d303c5334d0d8e595e1549d8c73b4cb0729a16
|
||||
size 1174430232
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 266240,
|
||||
"total_size": 16073105408
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal 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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2067
tokenizer_config.json
Normal file
2067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user