初始化项目，由ModelHub XC社区提供模型
Model: DarkArtsForge/Erebus-Nemo-12B Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.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
|
||||||
|
Erebus_Nemo.png filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
3
Erebus_Nemo.png
Normal file
3
Erebus_Nemo.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f95cf894462998b7b1c10317d5fa200b3a7533dd7c6745d8fbabdc35281a0638
|
||||||
|
size 1871843
|
||||||
270
README.md
Normal file
270
README.md
Normal file
@@ -0,0 +1,270 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- mistralai/Mistral-Nemo-Instruct-2407
|
||||||
|
- TheDrummer/Rocinante-X-12B-v1
|
||||||
|
- SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
|
||||||
|
- KOOWEEYUS/BlackSheep-RP-12B
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
- mistral
|
||||||
|
- nemo
|
||||||
|
- aether
|
||||||
|
- karcher
|
||||||
|
widget:
|
||||||
|
- text: "Erebus-Nemo 12B"
|
||||||
|
output:
|
||||||
|
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/I4UX52MpSo_Br3AqBu7Nk.png
|
||||||
|
---
|
||||||
|
|
||||||
|
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/RN39R7FzLokaWjKOH4IMO.mpga"></audio>
|
||||||
|
|
||||||
|
> [!CAUTION]
|
||||||
|
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **ChatML** or **Mistral Tekken** chat template.
|
||||||
|
>
|
||||||
|
|
||||||
|
<!DOCTYPE html>
|
||||||
|
<style>
|
||||||
|
body {
|
||||||
|
font-family: sans-serif;
|
||||||
|
color: #E0E0FF;
|
||||||
|
line-height: 1.6;
|
||||||
|
margin: 0;
|
||||||
|
padding: 0;
|
||||||
|
background-color: #0B0A18;
|
||||||
|
}
|
||||||
|
|
||||||
|
b, strong {
|
||||||
|
color: #9F80FF;
|
||||||
|
}
|
||||||
|
|
||||||
|
.cosmic-text {
|
||||||
|
color: #7DF9FF;
|
||||||
|
position: relative;
|
||||||
|
z-index: 2;
|
||||||
|
margin-left: 0.2em;
|
||||||
|
text-shadow: 0 0 15px #7DF9FF;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Section styling */
|
||||||
|
.section-container {
|
||||||
|
background-color: rgba(11, 10, 24, 0.8);
|
||||||
|
margin-bottom: 30px;
|
||||||
|
position: relative;
|
||||||
|
overflow: hidden;
|
||||||
|
border-bottom: 1px solid #9F80FF;
|
||||||
|
box-shadow: 0 4px 15px rgba(159, 128, 255, 0.1);
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-header {
|
||||||
|
display: flex;
|
||||||
|
align-items: center;
|
||||||
|
background-color: rgba(159, 128, 255, 0.06);
|
||||||
|
padding: 10px 20px;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-indicator {
|
||||||
|
width: 8px;
|
||||||
|
height: 20px;
|
||||||
|
background-color: #9F80FF;
|
||||||
|
margin-right: 15px;
|
||||||
|
box-shadow: 0 0 8px rgba(159, 128, 255, 0.4);
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-title {
|
||||||
|
font-family: 'Georgia', 'Times New Roman', serif;
|
||||||
|
color: #E0E0FF;
|
||||||
|
font-size: 1.4rem;
|
||||||
|
margin: 0;
|
||||||
|
letter-spacing: 1px;
|
||||||
|
font-weight: 400;
|
||||||
|
text-transform: capitalize;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-content {
|
||||||
|
padding: 20px;
|
||||||
|
font-family: sans-serif;
|
||||||
|
color: #E0E0FF;
|
||||||
|
line-height: 1.6;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Title styling */
|
||||||
|
.title-container {
|
||||||
|
background-color: #05040D;
|
||||||
|
position: relative;
|
||||||
|
overflow: hidden;
|
||||||
|
margin-bottom: 40px;
|
||||||
|
border-left: 3px solid #7DF9FF;
|
||||||
|
box-shadow: 0 6px 20px rgba(125, 249, 255, 0.15);
|
||||||
|
}
|
||||||
|
|
||||||
|
.title-wrapper {
|
||||||
|
position: relative;
|
||||||
|
z-index: 2;
|
||||||
|
padding: 25px 20px 30px 30px;
|
||||||
|
font-family: 'Georgia', 'Times New Roman', serif;
|
||||||
|
}
|
||||||
|
|
||||||
|
.title-main {
|
||||||
|
color: #E0E0FF;
|
||||||
|
font-size: 2.0rem;
|
||||||
|
font-weight: 700;
|
||||||
|
margin: 0;
|
||||||
|
letter-spacing: 2px;
|
||||||
|
display: inline-block;
|
||||||
|
position: relative;
|
||||||
|
text-transform: uppercase;
|
||||||
|
}
|
||||||
|
|
||||||
|
.glitchy-overlay {
|
||||||
|
position: absolute;
|
||||||
|
top: 0;
|
||||||
|
left: 0;
|
||||||
|
width: 100%;
|
||||||
|
height: 100%;
|
||||||
|
background-image: repeating-linear-gradient(0deg, rgba(0,0,0,0) 0, rgba(125, 249, 255, 0.08) 1px, rgba(0,0,0,0) 2px);
|
||||||
|
z-index: 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Subheading styling */
|
||||||
|
.subheading {
|
||||||
|
color: #D47CFF;
|
||||||
|
font-size: 1.1rem;
|
||||||
|
margin-top: 20px;
|
||||||
|
margin-bottom: 15px;
|
||||||
|
font-weight: 400;
|
||||||
|
border-bottom: 1px dashed rgba(212, 124, 255, 0.4);
|
||||||
|
display: inline-block;
|
||||||
|
text-transform: uppercase;
|
||||||
|
letter-spacing: 1px;
|
||||||
|
font-family: 'Georgia', 'Times New Roman', serif;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Links */
|
||||||
|
a {
|
||||||
|
color: #D47CFF;
|
||||||
|
text-decoration: none;
|
||||||
|
}
|
||||||
|
|
||||||
|
a:hover {
|
||||||
|
text-decoration: underline;
|
||||||
|
color: #7DF9FF;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Container */
|
||||||
|
.container {
|
||||||
|
max-width: 1200px;
|
||||||
|
margin: 20px auto;
|
||||||
|
padding: 40px 20px;
|
||||||
|
background-color: #05040D;
|
||||||
|
background-image:
|
||||||
|
radial-gradient(circle at 20% 80%, rgba(125, 249, 255, 0.05) 0%, transparent 50%),
|
||||||
|
radial-gradient(circle at 80% 20%, rgba(159, 128, 255, 0.05) 0%, transparent 50%);
|
||||||
|
min-height: calc(100vh - 40px);
|
||||||
|
border: 1px solid #9F80FF;
|
||||||
|
border-radius: 8px;
|
||||||
|
box-shadow: 0 8px 32px rgba(159, 128, 255, 0.15);
|
||||||
|
}
|
||||||
|
|
||||||
|
</style>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||||
|
<title>Erebus-Nemo 12B</title>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
|
||||||
|
<div class="container">
|
||||||
|
<div class="title-container">
|
||||||
|
<div class="glitchy-overlay"></div>
|
||||||
|
<div class="title-wrapper">
|
||||||
|
<h1 class="title-main">
|
||||||
|
<span class="cosmic-text">🐠 Erebus-Nemo 12B</span>
|
||||||
|
</h1>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/I4UX52MpSo_Br3AqBu7Nk.png" alt="ErebusNemo" style="width:100%; border-radius: 5px; margin-bottom: 30px;">
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">🌆 Overview</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
This is a <b>creative, uncensored</b> merge of pre-trained language models created using <a href="https://github.com/cg123/mergekit">mergekit</a>.
|
||||||
|
<br><br><b>Erebus Nemo 12B</b> is fully uncensored via the <code>normalize: false</code> setting. It has no refusals and should not require ablation or jailbreaks.
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">🔍 Merge Details</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
<b>Merge Method</b><br>
|
||||||
|
This model was merged using the <a href="https://huggingface.co/papers/2406.11617">della</a> merge method.<br><br>
|
||||||
|
<b>Models Merged</b><br>
|
||||||
|
The following models were included in the merge:
|
||||||
|
<ul>
|
||||||
|
<li><a href="https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407">mistralai/Mistral-Nemo-Instruct-2407</a></li>
|
||||||
|
<li><a href="https://huggingface.co/SuperbEmphasis/MN-12b-RP-Ink-RP-Longform">SuperbEmphasis/MN-12b-RP-Ink-RP-Longform</a></li>
|
||||||
|
<li><a href="https://huggingface.co/TheDrummer/Rocinante-X-12B-v1">TheDrummer/Rocinante-X-12B-v1</a></li>
|
||||||
|
<li><a href="https://huggingface.co/KOOWEEYUS/BlackSheep-RP-12B">KOOWEEYUS/BlackSheep-RP-12B</a></li>
|
||||||
|
</ul>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">⚙️ Configuration</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
The following YAML configuration was used to produce this model:
|
||||||
|
<pre style="font-family: monospace; white-space: pre; margin: 0;">
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
architecture: MistralForCausalLM
|
||||||
|
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
|
||||||
|
models:
|
||||||
|
- model: B:/12B/TheDrummer--Rocinante-X-12B-v1
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
merge_method: della
|
||||||
|
parameters:
|
||||||
|
lambda: 1.0
|
||||||
|
normalize: false
|
||||||
|
int8_mask: false
|
||||||
|
rescale: true
|
||||||
|
# seed: 420
|
||||||
|
dtype: float32
|
||||||
|
out_dtype: bfloat16
|
||||||
|
tokenizer:
|
||||||
|
source: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||||
|
# chat_template: "chatml"
|
||||||
|
name: 🐠 Erebus-Nemo 12B
|
||||||
|
```
|
||||||
|
|
||||||
|
</pre>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}
|
||||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"MistralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.56.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 131072
|
||||||
|
}
|
||||||
31
mergekit_config.yml
Normal file
31
mergekit_config.yml
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
architecture: MistralForCausalLM
|
||||||
|
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
|
||||||
|
models:
|
||||||
|
- model: B:/12B/TheDrummer--Rocinante-X-12B-v1
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B
|
||||||
|
parameters:
|
||||||
|
weight: 0.7
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
merge_method: della
|
||||||
|
parameters:
|
||||||
|
lambda: 1.0
|
||||||
|
normalize: false
|
||||||
|
int8_mask: false
|
||||||
|
rescale: true
|
||||||
|
# seed: 420
|
||||||
|
dtype: float32
|
||||||
|
out_dtype: bfloat16
|
||||||
|
tokenizer:
|
||||||
|
source: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||||
|
# chat_template: "chatml"
|
||||||
|
name: 🐠 Erebus-Nemo 12B
|
||||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:74de139757f1a2a8a58c2c4edc50bf77d888846606dd5d1d0bfe3cb6033bb4d3
|
||||||
|
size 4865489336
|
||||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d6e339452c40a8debf309a94f6bd332d2f8547f5b1de40b1a86678cf0a69f704
|
||||||
|
size 4907529456
|
||||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0f5662fca1338f35590d2f98d5df970c4b6e0e9e88ac91f3bd6b01d7079d64a2
|
||||||
|
size 4907529464
|
||||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3ce323e41e360c4ab6fefc9adb89d6908cbd070dfade058bd8ca38b56121f43a
|
||||||
|
size 4907529456
|
||||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d20de36519747bde9121272cd20f422379166310b079e23f53729aefb0e77522
|
||||||
|
size 4907529392
|
||||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 24495564800,
|
||||||
|
"mergekit_version": "0.1.4"
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
|
||||||
|
size 17078292
|
||||||
8020
tokenizer_config.json
Normal file
8020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user