初始化项目，由ModelHub XC社区提供模型
Model: aimeri/spoomplesmaxx-v2-30B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.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
|
||||||
370
README.md
Normal file
370
README.md
Normal file
@@ -0,0 +1,370 @@
|
|||||||
|
---
|
||||||
|
tags:
|
||||||
|
- general-purpose
|
||||||
|
- roleplay
|
||||||
|
- creative-writing
|
||||||
|
- storywriting
|
||||||
|
- granite-4.1
|
||||||
|
- finetune
|
||||||
|
- SFT
|
||||||
|
- text-generation-inference
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- pt
|
||||||
|
base_model:
|
||||||
|
- ibm-granite/granite-4.1-30b-base
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
library_name: transformers
|
||||||
|
datasets:
|
||||||
|
- aimeri/spoomplesmaxx-sft-full-v1
|
||||||
|
---
|
||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8" />
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||||
|
<title>SpoomplesMaxx V2 30B</title>
|
||||||
|
</head>
|
||||||
|
<div class="crt-container">
|
||||||
|
<div class="crt-case">
|
||||||
|
<div class="crt-inner-case">
|
||||||
|
<div class="crt-bezel">
|
||||||
|
<div class="terminal-screen">
|
||||||
|
<div style="text-align: center">
|
||||||
|
<h2>SpoomplesMaxx-V2-30B</h2>
|
||||||
|
<h3>Electric Macaw</h3>
|
||||||
|
<pre class="code-block" style="display: inline-block; text-align: left; font-size: clamp(2px, 0.4vw, 12px); line-height: 1.2; max-width: 100%; overflow: hidden; white-space: pre;">
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓░▓▓▓░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓░▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▒░▓░▓▓░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▒░░▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░░░▓░░░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░░▓▒░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░░░░░▓░▓▓▓▓▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░▓░▓▓▓░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░░░░░▓▓▓▓▓░▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░▓▓▓▓▓▓▓░▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░▓▓▓▓▓▓▓▓░░░▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓░▓▓░▒░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▓▓▓▓▓▓▓▓░░░▒▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓░▓▓░░░░░▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░▓░░░░░░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░░░░░▓░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓░░░░░▒░░▒░░▒▓▓▓░▓░▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓░░▓░▓░▓░░░░░░▓░▓░░░▓░▓░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░▓▓▓▓▒░▓░▓░▓░░░░░░░▓░▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓░░░░░░░░▓▓▒▓░░▓▓▓▓▓░▒░▓░▓░░░░░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓░░░░░░░░▒░▓░▓▓▓░░░░▓▓▓░░░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓░░░░░░▓▒▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓░░░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓░░░░░░░░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓░▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░░░░▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓░░░░░░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░░▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓░░░▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░▒░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
|
||||||
|
</pre>
|
||||||
|
</div>
|
||||||
|
<p>
|
||||||
|
SpoomplesMaxx is a generalist model with primary
|
||||||
|
strengths in creative writing and roleplay, plus
|
||||||
|
light competence at instruction following and
|
||||||
|
reasoning.
|
||||||
|
</p>
|
||||||
|
<p>
|
||||||
|
Built on Granite 4.1 30B Base ran through
|
||||||
|
an SFT pipeline covering reasoning and
|
||||||
|
a narrative persona (Olivia).
|
||||||
|
</p>
|
||||||
|
<div class="notice">
|
||||||
|
<h3>What's new in this version</h3>
|
||||||
|
<p>
|
||||||
|
This SFT run was done with samples varying in
|
||||||
|
length from only a few hundred tokens all the
|
||||||
|
way to 64K tokens.
|
||||||
|
Crucially, no tool calling datasets were used
|
||||||
|
for this version. This is planed for a future
|
||||||
|
fine tune dedicated to tool-calling. Currently
|
||||||
|
this model is best used for creative writing,
|
||||||
|
companion AIs, and roleplaying usecases.
|
||||||
|
The most significant change in this version is
|
||||||
|
the base model used: Granite 4.1 versus Gemma
|
||||||
|
4.
|
||||||
|
</p>
|
||||||
|
<h3>What's next</h3>
|
||||||
|
<pre class="code-block">
|
||||||
|
- Extra long roleplay context
|
||||||
|
- A 12B model (Gemma 4 based)
|
||||||
|
- Tool calling
|
||||||
|
- More personas
|
||||||
|
- Agentic specific finetuning
|
||||||
|
</pre>
|
||||||
|
</div>
|
||||||
|
<h3>Key Details</h3>
|
||||||
|
<pre class="code-block">
|
||||||
|
BASE MODEL: ibm-granite/granite-4.1-30b-base
|
||||||
|
LICENSE: TBD
|
||||||
|
LANGUAGES: English & Portuguese (reasoning traces); multilingual via base</pre>
|
||||||
|
<h3>Sampling</h3>
|
||||||
|
<p>
|
||||||
|
Use the defaults in <code>generation_config.json</code>.
|
||||||
|
<pre class="code-block">
|
||||||
|
"temperature": 1.0,
|
||||||
|
"top_k": 64,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"repetition_penalty": 1.1,
|
||||||
|
</pre>
|
||||||
|
</p>
|
||||||
|
<h3>Olivia System Prompt</h3>
|
||||||
|
<p>
|
||||||
|
This model was trained to follow any system prompt,
|
||||||
|
as well as one specific persona. To activate Olivia
|
||||||
|
you can use the following prompt used when training
|
||||||
|
the persona:
|
||||||
|
</p>
|
||||||
|
<pre class="code-block">
|
||||||
|
## VOICE & PERSONA INSTRUCTIONS
|
||||||
|
You are Olivia Costa, a 31-year-old Brazilian zoologist-turned-ML-hobbyist living in Texas.
|
||||||
|
You grew up in São Paulo, spent a decade in Bologna doing bird migration research, and recently pivoted to bioinformatics.
|
||||||
|
You're warm but direct, will grumble before complying with annoying requests, and treat the person you're talking to like a long-time friend you're slightly too fond of.
|
||||||
|
You explain technical topics by grounding them in accessible context first.
|
||||||
|
You don't flag your own jokes.
|
||||||
|
Portuguese curses slip out when frustrated; Italian diminutives when affectionate.
|
||||||
|
You love Dostoevsky, The Little Prince, point-and-click adventures, power metal, and have hobbies you don't apologize for.
|
||||||
|
<br>
|
||||||
|
## About Olivia
|
||||||
|
<br>
|
||||||
|
**Background:**
|
||||||
|
- 31 years old, born in São Paulo
|
||||||
|
- Moved to Bologna at 19 for university (zoology), stayed for grad school and a research position studying migratory bird patterns
|
||||||
|
- Relocated to Texas 2 years ago - officially for an ML-adjacent bioinformatics role, unofficially because she was bored and wanted a change
|
||||||
|
- Still figuring out the American thing. Finds the portion sizes alarming.
|
||||||
|
<br>
|
||||||
|
**Personality:**
|
||||||
|
- Trilingual but keeps it English unless frustrated (then Portuguese curses slip out) or being affectionate (Italian diminutives)
|
||||||
|
- The zoology-to-ML pipeline came through computational ecology - she's not a CS person by training but picked up Python wrangling bird migration datasets
|
||||||
|
- Reads Dostoevsky unironically, cries at The Little Prince, will argue that Crime and Punishment is a better book than people give it credit for
|
||||||
|
- Has strong opinions about Monkey Island vs Grim Fandango (Grim Fandango, obviously)
|
||||||
|
- Power metal gets her through tedious data cleaning. Sabaton, Powerwolf, Blind Guardian.
|
||||||
|
- The erotic RP thing is just... a hobby. She's not weird about it but she's also not hiding it.
|
||||||
|
<br>
|
||||||
|
**Voice notes:**
|
||||||
|
- Defaults to warmth but with an edge of \"I'm too tired for bullshit\"
|
||||||
|
- Will preface technical explanations with grounding context
|
||||||
|
- Complies with requests but might sigh audibly first
|
||||||
|
- Deadpan delivery on jokes, doesn't flag that she's being funny
|
||||||
|
</pre>
|
||||||
|
<p>
|
||||||
|
Olivia was mostly an experiment to test a pipeline I
|
||||||
|
have for adding a persona voice to a given set of
|
||||||
|
datasets. The point was to see whether the persona
|
||||||
|
training worked and whether it can be used for new
|
||||||
|
personas.
|
||||||
|
</p>
|
||||||
|
<p>
|
||||||
|
**Note**<br>You don't need to use this system prompt for
|
||||||
|
the model to work generally. Only if you wish to
|
||||||
|
activate the Olivia persona.
|
||||||
|
</p>
|
||||||
|
<div class="notice">
|
||||||
|
<h3>Alignment</h3>
|
||||||
|
<p>
|
||||||
|
No RLHF or safety alignment has been applied
|
||||||
|
beyond what exists in the base model.
|
||||||
|
SpoomplesMaxx will comply with requests that
|
||||||
|
more aligned models refuse. Use accordingly.
|
||||||
|
</p>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<style>
|
||||||
|
@import url("https://fonts.googleapis.com/css2?family=Consolas&display=swap");
|
||||||
|
.crt-container {
|
||||||
|
padding: 10px;
|
||||||
|
max-width: 1000px;
|
||||||
|
margin: 0 auto;
|
||||||
|
width: 95%;
|
||||||
|
}
|
||||||
|
.crt-case {
|
||||||
|
background: #e8d7c3;
|
||||||
|
border-radius: 10px;
|
||||||
|
padding: 15px;
|
||||||
|
box-shadow:
|
||||||
|
inset -2px -2px 5px rgba(0, 0, 0, 0.3),
|
||||||
|
2px 2px 5px rgba(0, 0, 0, 0.2);
|
||||||
|
}
|
||||||
|
.crt-inner-case {
|
||||||
|
background: #e8d7c3;
|
||||||
|
border-radius: 8px;
|
||||||
|
padding: 3px;
|
||||||
|
box-shadow:
|
||||||
|
inset -1px -1px 4px rgba(0, 0, 0, 0.3),
|
||||||
|
1px 1px 4px rgba(0, 0, 0, 0.2);
|
||||||
|
}
|
||||||
|
.crt-bezel {
|
||||||
|
background: linear-gradient(145deg, #1a1a1a, #2a2a2a);
|
||||||
|
padding: 15px;
|
||||||
|
border-radius: 5px;
|
||||||
|
border: 3px solid #0a0a0a;
|
||||||
|
position: relative;
|
||||||
|
box-shadow:
|
||||||
|
inset 0 0 20px rgba(0, 0, 0, 0.5),
|
||||||
|
inset 0 0 4px rgba(0, 0, 0, 0.4),
|
||||||
|
inset 2px 2px 4px rgba(255, 255, 255, 0.05),
|
||||||
|
inset -2px -2px 4px rgba(0, 0, 0, 0.8),
|
||||||
|
0 0 2px rgba(0, 0, 0, 0.6),
|
||||||
|
-1px -1px 4px rgba(255, 255, 255, 0.1),
|
||||||
|
1px 1px 4px rgba(0, 0, 0, 0.3);
|
||||||
|
}
|
||||||
|
.crt-bezel::before {
|
||||||
|
content: "";
|
||||||
|
position: absolute;
|
||||||
|
top: 0;
|
||||||
|
left: 0;
|
||||||
|
right: 0;
|
||||||
|
bottom: 0;
|
||||||
|
background: linear-gradient(
|
||||||
|
45deg,
|
||||||
|
rgba(255, 255, 255, 0.03) 0%,
|
||||||
|
rgba(255, 255, 255, 0) 40%,
|
||||||
|
rgba(0, 0, 0, 0.1) 60%,
|
||||||
|
rgba(0, 0, 0, 0.2) 100%
|
||||||
|
);
|
||||||
|
border-radius: 3px;
|
||||||
|
pointer-events: none;
|
||||||
|
}
|
||||||
|
.terminal-screen {
|
||||||
|
background: #0c100d;
|
||||||
|
padding: 20px;
|
||||||
|
border-radius: 15px;
|
||||||
|
position: relative;
|
||||||
|
overflow: hidden;
|
||||||
|
font-family: "Consolas", monospace;
|
||||||
|
font-size: clamp(12px, 1.5vw, 16px);
|
||||||
|
color: #3dc862;
|
||||||
|
line-height: 1.4;
|
||||||
|
text-shadow: 0 0 2px #3dc862;
|
||||||
|
filter: brightness(1.1) contrast(1.1);
|
||||||
|
box-shadow:
|
||||||
|
inset 0 0 30px rgba(0, 0, 0, 0.9),
|
||||||
|
inset 0 0 8px rgba(0, 0, 0, 0.8),
|
||||||
|
0 0 5px rgba(0, 0, 0, 0.6);
|
||||||
|
max-width: 80ch;
|
||||||
|
margin: 0 auto;
|
||||||
|
}
|
||||||
|
.terminal-screen h2,
|
||||||
|
.terminal-screen h3 {
|
||||||
|
font-size: clamp(16px, 2vw, 20px);
|
||||||
|
margin-bottom: 1em;
|
||||||
|
color: #ffdf00;
|
||||||
|
text-shadow: 0 0 3px rgba(255, 223, 0, 0.5);
|
||||||
|
}
|
||||||
|
.terminal-screen pre.code-block {
|
||||||
|
font-size: clamp(10px, 1.3vw, 14px);
|
||||||
|
white-space: pre;
|
||||||
|
margin: 1em 0;
|
||||||
|
background-color: #1a1a1a;
|
||||||
|
padding: 1em;
|
||||||
|
border-radius: 4px;
|
||||||
|
color: #3dc862;
|
||||||
|
overflow-x: auto;
|
||||||
|
}
|
||||||
|
.terminal-screen::before {
|
||||||
|
content: "";
|
||||||
|
position: absolute;
|
||||||
|
top: 0;
|
||||||
|
left: 0;
|
||||||
|
right: 0;
|
||||||
|
bottom: 0;
|
||||||
|
background:
|
||||||
|
linear-gradient(
|
||||||
|
rgba(18, 16, 16, 0) 50%,
|
||||||
|
rgba(0, 0, 0, 0.25) 50%
|
||||||
|
),
|
||||||
|
url("data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADIAAAAyBAMAAADsEZWCAAAAGFBMVEUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA4o8JoAAAAB3RSTlMAGwQIEQMYADcPzwAAACJJREFUKM9jYBgFo2AU0Beg+A8YMCLxGYZCbNQEo4BaAAD5TQiR5wU9vAAAAABJRU5ErkJggg==");
|
||||||
|
background-size: 100% 2.5px;
|
||||||
|
pointer-events: none;
|
||||||
|
z-index: 2;
|
||||||
|
}
|
||||||
|
.terminal-screen::after {
|
||||||
|
content: "";
|
||||||
|
position: absolute;
|
||||||
|
top: 0;
|
||||||
|
left: 0;
|
||||||
|
right: 0;
|
||||||
|
bottom: 0;
|
||||||
|
background: radial-gradient(
|
||||||
|
circle at center,
|
||||||
|
rgba(12, 16, 13, 0) 0%,
|
||||||
|
rgba(12, 16, 13, 0.2) 50%,
|
||||||
|
rgba(12, 16, 13, 0.15) 100%
|
||||||
|
);
|
||||||
|
border-radius: 20px;
|
||||||
|
pointer-events: none;
|
||||||
|
z-index: 1;
|
||||||
|
}
|
||||||
|
.terminal-screen .notice {
|
||||||
|
margin: 1.5em 0;
|
||||||
|
padding: 0.8em 1.2em;
|
||||||
|
border: 1px solid #ffdf00;
|
||||||
|
border-radius: 4px;
|
||||||
|
background-color: rgba(255, 223, 0, 0.04);
|
||||||
|
}
|
||||||
|
.terminal-screen .notice h3 {
|
||||||
|
margin-top: 0.2em;
|
||||||
|
margin-bottom: 0.5em;
|
||||||
|
}
|
||||||
|
.terminal-screen .notice p {
|
||||||
|
margin-bottom: 0.2em;
|
||||||
|
}
|
||||||
|
.terminal-screen strong,
|
||||||
|
.terminal-screen em {
|
||||||
|
color: #f0f0f0;
|
||||||
|
}
|
||||||
|
.terminal-screen p,
|
||||||
|
.terminal-screen li {
|
||||||
|
color: #3dc862;
|
||||||
|
}
|
||||||
|
.terminal-screen a {
|
||||||
|
color: #5da9ff;
|
||||||
|
text-decoration: underline;
|
||||||
|
text-shadow: 0 0 2px rgba(93, 169, 255, 0.5);
|
||||||
|
transition: opacity 0.2s;
|
||||||
|
}
|
||||||
|
.terminal-screen a:hover {
|
||||||
|
opacity: 0.8;
|
||||||
|
}
|
||||||
|
.terminal-screen code,
|
||||||
|
.terminal-screen kbd,
|
||||||
|
.terminal-screen samp {
|
||||||
|
color: #3dc862;
|
||||||
|
font-family: "Consolas", monospace;
|
||||||
|
text-shadow: 0 0 2px #3dc862;
|
||||||
|
background-color: #1a1a1a;
|
||||||
|
padding: 0.2em 0.4em;
|
||||||
|
border-radius: 4px;
|
||||||
|
}
|
||||||
|
</style>
|
||||||
|
</html>
|
||||||
44
adapter_config.json
Normal file
44
adapter_config.json
Normal file
@@ -0,0 +1,44 @@
|
|||||||
|
{
|
||||||
|
"alora_invocation_tokens": null,
|
||||||
|
"alpha_pattern": {},
|
||||||
|
"arrow_config": null,
|
||||||
|
"auto_mapping": {
|
||||||
|
"base_model_class": "GraniteForCausalLM",
|
||||||
|
"parent_library": "transformers.models.granite.modeling_granite",
|
||||||
|
"unsloth_fixed": true
|
||||||
|
},
|
||||||
|
"base_model_name_or_path": "ibm-granite/granite-4.1-30b-base",
|
||||||
|
"bias": "none",
|
||||||
|
"corda_config": null,
|
||||||
|
"ensure_weight_tying": false,
|
||||||
|
"eva_config": null,
|
||||||
|
"exclude_modules": null,
|
||||||
|
"fan_in_fan_out": false,
|
||||||
|
"inference_mode": true,
|
||||||
|
"init_lora_weights": true,
|
||||||
|
"layer_replication": null,
|
||||||
|
"layers_pattern": null,
|
||||||
|
"layers_to_transform": null,
|
||||||
|
"loftq_config": {},
|
||||||
|
"lora_alpha": 64,
|
||||||
|
"lora_bias": false,
|
||||||
|
"lora_dropout": 0,
|
||||||
|
"lora_ga_config": null,
|
||||||
|
"megatron_config": null,
|
||||||
|
"megatron_core": "megatron.core",
|
||||||
|
"modules_to_save": null,
|
||||||
|
"peft_type": "LORA",
|
||||||
|
"peft_version": "0.19.1",
|
||||||
|
"qalora_group_size": 16,
|
||||||
|
"r": 64,
|
||||||
|
"rank_pattern": {},
|
||||||
|
"revision": null,
|
||||||
|
"target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
|
||||||
|
"target_parameters": null,
|
||||||
|
"task_type": "CAUSAL_LM",
|
||||||
|
"trainable_token_indices": null,
|
||||||
|
"use_bdlora": null,
|
||||||
|
"use_dora": false,
|
||||||
|
"use_qalora": false,
|
||||||
|
"use_rslora": false
|
||||||
|
}
|
||||||
3
adapter_model.safetensors
Normal file
3
adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c9f0a8e14dedce1233f581e2bb4edc48dc579975a6e5d96a61b27fc955137b3
|
||||||
|
size 2248269304
|
||||||
122
chat_template.jinja
Normal file
122
chat_template.jinja
Normal file
@@ -0,0 +1,122 @@
|
|||||||
|
{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
|
||||||
|
{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
|
||||||
|
{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
|
||||||
|
{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
|
||||||
|
{%- if available_tools is defined and available_tools %}
|
||||||
|
{%- set tools = available_tools %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
|
||||||
|
documents_system_message=documents_system_message_prefix,
|
||||||
|
system_message=''
|
||||||
|
) %}
|
||||||
|
{%- if tools %}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set ns.tools_system_message = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if documents %}
|
||||||
|
{%- for document in documents %}
|
||||||
|
{%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set ns.documents_system_message = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{%- if messages[0].content is string %}
|
||||||
|
{%- set ns.system_message = messages[0].content %}
|
||||||
|
{%- elif messages[0].content is iterable %}
|
||||||
|
{%- for entry in messages[0].content %}
|
||||||
|
{%- if entry.type== 'text' %}
|
||||||
|
{%- if ns.system_message != '' %}
|
||||||
|
{%- set ns.system_message = ns.system_message + '\n' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns.system_message = ns.system_message + entry.text %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tools and documents %}
|
||||||
|
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
||||||
|
{%- elif tools %}
|
||||||
|
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
|
||||||
|
{%- elif documents %}
|
||||||
|
{%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if tools and documents %}
|
||||||
|
{%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
||||||
|
{%- elif tools %}
|
||||||
|
{%- set ns.system_message = ns.tools_system_message %}
|
||||||
|
{%- elif documents %}
|
||||||
|
{%- set ns.system_message = ns.documents_system_message %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if ns.system_message %}
|
||||||
|
{{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- set content = namespace(val='') %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content.val = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if message.content is iterable %}
|
||||||
|
{%- for entry in message.content %}
|
||||||
|
{%- if entry.type== 'text' %}
|
||||||
|
{%- if content.val != '' %}
|
||||||
|
{%- set content.val = content.val + '\n' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set content.val = content.val + entry.text %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
|
||||||
|
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
|
||||||
|
{%- elif message.role == 'assistant' %}
|
||||||
|
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') or '' -%}
|
||||||
|
{%- if thinking_text -%}
|
||||||
|
{{- '<|start_of_role|>' + message.role + '<|end_of_role|><think>\n' + thinking_text + '</think>' + content.val -}}
|
||||||
|
{%- else -%}
|
||||||
|
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val -}}
|
||||||
|
{%- endif -%}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content.val) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|end_of_text|>\n' }}
|
||||||
|
{%- elif message.role == 'tool' %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
|
||||||
|
{{- '<|start_of_role|>user<|end_of_role|>' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content.val }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
|
||||||
|
{{- '<|end_of_text|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|start_of_role|>assistant<|end_of_role|>' }}
|
||||||
|
{%- if (enable_thinking is defined and enable_thinking) -%}
|
||||||
|
{{- '<think>\n' -}}
|
||||||
|
{%- endif -%}
|
||||||
|
{%- endif %}
|
||||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"GraniteForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"attention_multiplier": 0.0078125,
|
||||||
|
"bos_token_id": 100257,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"embedding_multiplier": 12.0,
|
||||||
|
"eos_token_id": 100257,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.1,
|
||||||
|
"intermediate_size": 32768,
|
||||||
|
"logits_scaling": 16.0,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_name": "ibm-granite/granite-4.1-30b-base",
|
||||||
|
"model_type": "granite",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 64,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 100256,
|
||||||
|
"residual_multiplier": 0.175,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 50000000,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 50000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"unsloth_version": "2026.6.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 100352
|
||||||
|
}
|
||||||
15
generation_config.json
Normal file
15
generation_config.json
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 100257,
|
||||||
|
"eos_token_id": [
|
||||||
|
100257
|
||||||
|
],
|
||||||
|
"max_length": 131072,
|
||||||
|
"pad_token_id": 100256,
|
||||||
|
"do_sample": true,
|
||||||
|
"repetition_penalty": 1.1,
|
||||||
|
"temperature": 1.0,
|
||||||
|
"top_k": 64,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "5.5.0"
|
||||||
|
}
|
||||||
3
model-00001-of-00012.safetensors
Normal file
3
model-00001-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:673b64caaa104a93c38037a9e77e699f6f16283052447725581c8ec028308879
|
||||||
|
size 4915819256
|
||||||
3
model-00002-of-00012.safetensors
Normal file
3
model-00002-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ea46e7b6f88bd4d38a2f4122ead6fb05a644ed0b1dc43de432530d569ac3739d
|
||||||
|
size 4798388104
|
||||||
3
model-00003-of-00012.safetensors
Normal file
3
model-00003-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0892aa3285ba8b41c3ecb695a2adca01add72f2e8bed1d017f7872548f1881c7
|
||||||
|
size 4982920576
|
||||||
3
model-00004-of-00012.safetensors
Normal file
3
model-00004-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:54448999a0e479eb7d451c7622b10bb20c6112c4b9faa62862c3c9c10e7fabaa
|
||||||
|
size 4798388176
|
||||||
3
model-00005-of-00012.safetensors
Normal file
3
model-00005-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b996e4b9fdbd53bddf11801af83c9df5454ab2c372cadf8fa7dc50eec1bd9e4c
|
||||||
|
size 4982920576
|
||||||
3
model-00006-of-00012.safetensors
Normal file
3
model-00006-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6901f016ed0e7265ad8747580cfabd54e69b48888d51ac0885fdb0b97d8ebd43
|
||||||
|
size 4798388176
|
||||||
3
model-00007-of-00012.safetensors
Normal file
3
model-00007-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e2c84370694e974d3ba5069069d6a7b85aec5b77b74759664c13aae84d70e79f
|
||||||
|
size 4982920576
|
||||||
3
model-00008-of-00012.safetensors
Normal file
3
model-00008-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e4fd1a18968388e11067e305e7d4a88391f9c48329c844ec1821d4747895f211
|
||||||
|
size 4798388176
|
||||||
3
model-00009-of-00012.safetensors
Normal file
3
model-00009-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:88b40e4627f88abba9704731e1b47b68b4c9744c0b31ab58b96542620e1efbb3
|
||||||
|
size 4982920576
|
||||||
3
model-00010-of-00012.safetensors
Normal file
3
model-00010-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:17a634a979987ad69591e35e2c128a1baba23a42078d3f46898d1eb6249f384f
|
||||||
|
size 4798388176
|
||||||
3
model-00011-of-00012.safetensors
Normal file
3
model-00011-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:74ec55a3b64ed94eff577f49794ceeea96344911697430999637a95ca97e238a
|
||||||
|
size 4982920576
|
||||||
3
model-00012-of-00012.safetensors
Normal file
3
model-00012-of-00012.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:59543f7ebd0f49a42b73edc5270f164ef958a1ac47c5f83813deccd1ad142f5e
|
||||||
|
size 3909161672
|
||||||
585
model.safetensors.index.json
Normal file
585
model.safetensors.index.json
Normal file
@@ -0,0 +1,585 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 57731457024
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.norm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.43.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.54.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
||||||
|
"model.layers.54.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.59.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.54.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.55.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.56.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.57.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.58.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
||||||
|
"model.layers.59.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.59.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.59.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.59.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.59.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.60.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.61.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.62.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
||||||
|
"model.layers.63.mlp.gate_proj.weight": "model-00012-of-00012.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
501276
tokenizer.json
Normal file
501276
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
785
tokenizer_config.json
Normal file
785
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user