suayptalha/Maestro-R1-Llama-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: suayptalha/Maestro-R1-Llama-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 07:18:14 +08:00
commit e814a963d3
20 changed files with 3150 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

BIN
Maestro-Logo.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 204 KiB

631
README.md Normal file
View File

@@ -0,0 +1,631 @@
---
license: mit
datasets:
- ServiceNow-AI/R1-Distill-SFT
language:
- en
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
pipeline_tag: text-generation
library_name: transformers
tags:
- unsloth
- trl
- sft
---
<!DOCTYPE html>
<style>
ebody {
font-family: 'Quicksand', sans-serif;
background: linear-gradient(135deg, #FF69B4 0%, #800080 100%);
color: #FFFFFF;
margin: 0;
padding: 0;
font-size: 16px;
min-height: 100vh;
}
.container {
margin: 20px;
background-color: rgba(28, 14, 36, 0.95);
padding: 20px;
border-radius: 12px;
box-shadow: 0 4px 20px rgba(255, 105, 180, 0.4);
border: 1px solid rgba(255, 105, 180, 0.4);
outline: 1px solid rgba(255, 105, 180, 0.7);
outline-offset: -1px;
position: relative;
backdrop-filter: blur(10px);
}
.container::before {
content: '';
position: absolute;
top: -1px;
left: -1px;
right: -1px;
bottom: -1px;
border: 1px solid rgba(255, 105, 180, 0.98);
border-radius: 12px;
pointer-events: none;
animation: borderGlow 2s ease-in-out infinite;
}
@keyframes borderGlow {
0% {
box-shadow: 0 0 5px rgba(255, 105, 180, 0.98);
}
50% {
box-shadow: 0 0 20px rgba(255, 105, 180, 0.98);
}
100% {
box-shadow: 0 0 5px rgba(255, 105, 180, 0.98);
}
}
.header h1 {
font-size: 28px;
color: #FF69B4;
margin: 0 0 20px 0;
text-shadow: 0 0 15px rgba(255, 105, 180, 0.8);
letter-spacing: 1px;
}
.update-section {
margin-top: 30px;
}
.update-section h2, h2 {
font-size: 24px;
color: #FF69B4;
text-shadow: 0 0 15px rgba(255, 105, 180, 0.8);
letter-spacing: 0.5px;
}
.update-section p {
font-size: 16px;
line-height: 1.6;
color: #FFE1FF;
}
.info p {
color: #FFE1FF;
line-height: 1.6;
font-size: 16px;
}
.info img {
width: 100%;
border-radius: 10px;
margin-bottom: 15px;
box-shadow: 0 0 30px rgba(255, 105, 180, 0.5);
border: 1px solid rgba(255, 105, 180, 0.4);
outline: 1px solid rgba(255, 105, 180, 0.7);
outline-offset: -1px;
transition: transform 0.3s ease, box-shadow 0.3s ease;
}
.info img:hover {
transform: scale(1.01);
box-shadow: 0 0 40px rgba(255, 105, 180, 0.6);
}
a {
color: #00FFEE;
text-decoration: none;
transition: color 0.3s ease;
}
a:hover {
color: #FF1493;
}
.button {
display: inline-block;
background: linear-gradient(45deg, rgba(255, 105, 180, 0.9), rgba(128, 0, 128, 0.9));
color: #FFFFFF;
padding: 12px 24px;
border-radius: 5px;
cursor: pointer;
text-decoration: none;
transition: all 0.3s ease;
border: 1px solid rgba(255, 105, 180, 0.4);
}
.button:hover {
background: linear-gradient(45deg, rgba(255, 105, 180, 1), rgba(128, 0, 128, 1));
box-shadow: 0 0 20px rgba(255, 105, 180, 0.7);
transform: translateY(-2px);
}
pre {
background-color: rgba(28, 14, 36, 0.95);
padding: 15px;
border-radius: 5px;
overflow-x: auto;
border: 1px solid rgba(255, 20, 147, 0.3);
outline: 1px solid rgba(255, 20, 147, 0.6);
outline-offset: -1px;
}
code {
font-family: 'Courier New', monospace;
color: #FFE1FF;
}
.info-grid {
display: grid;
grid-template-columns: repeat(3, 1fr);
gap: 15px;
}
.creator-section {
margin: 20px 0;
}
.creator-badge {
display: inline-flex;
align-items: center;
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 10px 15px;
}
.creator-label {
color: #FFE1FF;
font-size: 14px;
margin-right: 8px;
}
.creator-link {
display: flex;
align-items: center;
gap: 5px;
color: #00FFEE;
text-decoration: none;
transition: all 0.3s ease;
}
.creator-name {
font-weight: 600;
}
.creator-arrow {
font-size: 16px;
transition: transform 0.3s ease;
}
.creator-link:hover {
color: #FF1493;
}
.creator-link:hover .creator-arrow {
transform: translateX(3px);
}
.model-info {
margin-top: 30px;
}
.name-legend {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 20px;
margin: 20px 0;
}
.name-legend h3 {
color: #FF1493;
font-size: 18px;
margin: 0 0 15px 0;
}
.legend-grid {
display: grid;
gap: 12px;
}
.legend-item {
display: flex;
align-items: baseline;
gap: 10px;
}
.legend-key {
color: #00FFEE;
font-weight: 600;
min-width: 80px;
}
.legend-value {
color: #FFE1FF;
}
.model-description {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 20px;
}
.model-description p {
margin: 0 0 15px 0;
line-height: 1.6;
}
.model-description p:last-child {
margin-bottom: 0;
}
.section-container {
margin: 40px 0;
}
.info-card {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
overflow: hidden;
}
.info-header {
background: rgba(255, 20, 147, 0.1);
padding: 20px;
border-bottom: 1px solid rgba(255, 20, 147, 0.3);
}
.info-header h3 {
color: #FF1493;
margin: 0 0 10px 0;
font-size: 20px;
text-shadow: 0 0 5px rgba(255, 20, 147, 0.3);
}
.model-tags {
display: flex;
gap: 8px;
flex-wrap: wrap;
}
.model-tag {
background: rgba(0, 255, 238, 0.1);
color: #00FFEE;
padding: 4px 8px;
border-radius: 4px;
font-size: 12px;
border: 1px solid rgba(0, 255, 238, 0.2);
}
.model-composition {
padding: 20px;
border-bottom: 1px solid rgba(255, 20, 147, 0.3);
}
.model-composition h4 {
color: #FF1493;
margin: 0 0 15px 0;
font-size: 16px;
}
.composition-list {
list-style: none;
padding: 0;
margin: 0;
display: grid;
gap: 10px;
}
.composition-list li {
color: #FFE1FF;
display: flex;
align-items: baseline;
gap: 8px;
}
.model-component {
color: #00FFEE;
font-weight: 500;
min-width: 120px;
}
.template-card {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 15px;
}
.template-item {
display: flex;
align-items: center;
gap: 12px;
}
.template-icon {
width: 24px;
height: 24px;
opacity: 0.8;
}
.template-content {
display: flex;
align-items: baseline;
gap: 8px;
}
.template-link {
color: #00FFEE;
text-decoration: none;
font-weight: 500;
display: flex;
align-items: center;
gap: 5px;
}
.template-author {
color: rgba(255, 225, 255, 0.7);
font-size: 14px;
}
.quantized-container {
display: grid;
gap: 20px;
}
.quantized-section {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 20px;
}
.quantized-section h3 {
color: #FF1493;
font-size: 18px;
margin: 0 0 15px 0;
}
.quantized-items {
display: grid;
gap: 12px;
}
.quantized-item {
display: flex;
align-items: baseline;
gap: 10px;
}
.quantized-item .author {
color: rgba(255, 225, 255, 0.7);
min-width: 100px;
}
.multi-links {
display: flex;
align-items: center;
gap: 8px;
}
.separator {
color: rgba(255, 225, 255, 0.5);
}
.config-container {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
overflow: hidden;
}
.config-header {
background: rgba(255, 20, 147, 0.1);
padding: 15px 20px;
border-bottom: 1px solid rgba(255, 20, 147, 0.3);
}
.model-name {
color: #FF1493;
font-weight: 600;
}
.config-content {
padding: 20px;
}
.config-item {
display: flex;
flex-direction: column;
gap: 5px;
margin-bottom: 15px;
}
.config-label {
color: #00FFEE;
font-size: 14px;
font-weight: 500;
}
.config-value {
color: #FFE1FF;
font-family: 'Courier New', monospace;
}
.config-models {
margin-top: 20px;
}
.model-list {
list-style: none;
padding: 0;
margin: 10px 0 0 0;
}
.model-list li {
color: #FFE1FF;
font-family: 'Courier New', monospace;
padding: 5px 0;
padding-left: 20px;
position: relative;
}
.model-list li::before {
content: '-';
position: absolute;
left: 0;
color: #00FFEE;
}
.link-arrow {
display: inline-block;
transition: transform 0.3s ease;
}
a:hover .link-arrow {
transform: translateX(3px);
}
.benchmark-notification {
background: rgba(255, 20, 147, 0.15);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
margin-bottom: 20px;
padding: 12px;
animation: glowPulse 2s infinite;
}
.notification-content {
display: flex;
align-items: center;
justify-content: center;
gap: 10px;
text-align: center;
}
.notification-icon {
font-size: 20px;
}
.notification-text {
color: #FFE1FF;
font-size: 16px;
font-weight: 500;
display: flex;
flex-direction: column;
align-items: center;
gap: 5px;
}
.benchmark-link {
color: #00FFEE;
text-decoration: none;
font-size: 14px;
padding: 4px 8px;
border-radius: 4px;
transition: all 0.3s ease;
border: 1px solid rgba(0, 255, 238, 0.3);
}
.benchmark-link:hover {
background: rgba(0, 255, 238, 0.1);
border-color: rgba(0, 255, 238, 0.5);
color: #00FFEE;
text-shadow: 0 0 5px rgba(0, 255, 238, 0.5);
}
@keyframes glowPulse {
0% {
box-shadow: 0 0 5px rgba(255, 20, 147, 0.3);
}
50% {
box-shadow: 0 0 15px rgba(255, 20, 147, 0.5);
}
100% {
box-shadow: 0 0 5px rgba(255, 20, 147, 0.3);
}
}
.review-card {
background: rgba(28, 14, 36, 0.95);
border: 1px solid rgba(255, 20, 147, 0.3);
border-radius: 8px;
padding: 15px;
margin-bottom: 15px;
}
.review-card:last-child {
margin-bottom: 0;
}
</style>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Maestro-R1-Llama-8B</title>
<link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
<link href="styles.css" rel="stylesheet">
</head>
<body>
<div class="container">
<div class="header">
<h1>Maestro-R1-Llama-8B</h1>
</div>
<div class="info">
<img src="Maestro-Logo.jpg" alt="Model banner">
<div class="creator-section">
<div class="creator-badge">
<span class="creator-label">Created by</span>
<a href="https://huggingface.co/suayptalha" target="_blank" class="creator-link">
<span class="creator-name">suayptalha</span>
<span class="creator-arrow">→</span>
</a>
</div>
</div>
<div class="model-info">
<h2>Model Information</h2>
<div class="info-card">
<div class="info-header">
<h3>Maestro-R1-Llama-8B</h3>
<div class="model-tags">
<span class="model-tag">Maestro-R1-Llama-8B</span>
<span class="model-tag">deepseek-ai/DeepSeek-R1-Distill-Llama-8B</span>
<span class="model-tag">8B Parameters</span>
</div>
</div>
<div class="model-composition">
<h4>Base Model</h4>
<ul class="composition-list">
<li><span class="model-component"><a href="deepseek-ai/DeepSeek-R1-Distill-Llama-8B" target="_blank">DeepSeek-R1-Distill-Llama-8B</a></span></li>
</ul>
</div>
<div class="model-description">
Maestro-R1-Llama-8B is a powerful language model fine-tuned from DeepSeek-R1-Distill-Llama-8B, a distilled model based on the Llama-3 architecture. DeepSeek-R1-Distill-Llama-8B itself is derived from the Llama-3 architecture, with a distillation process from DeepSeek-R1, utilizing a large corpus of diverse data. This distillation enables the model to retain strong reasoning capabilities while maintaining a smaller parameter count.
<br>
Maestro-R1-Llama-8B builds on this foundation, further enhancing its performance through fine-tuning on the ServiceNow-AI/R1-Distill-SFT dataset. This fine-tuning step sharpens the model's ability to handle specialized tasks and improves its reasoning, problem-solving, and code generation capabilities. The combination of the distilled base model and domain-specific fine-tuning makes Maestro-R1-Llama-8B an efficient and robust model, excelling across a wide range of language tasks.
<br>
DeepSeek-R1 Paper Link: https://arxiv.org/abs/2501.12948
</div>
<div class="model-composition">
<h4>Loss Graph</h4>
<img src="maestro-r1-llama-loss.png" alt="Model banner">
</div>
</div>
<div class="support-section">
<h2>Support & Community:</h2>
<div class="support-buttons">
<a href="https://buymeacoffee.com/suayptalha" target="_blank" class="button">
Buy me a coffee
</a>
<a href="https://discord.com/users/suaypt" target="_blank" class="button">
suayptalha - Discord
</a>
</div>
</div>
</div>
</div>
</body>
</html>

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128004,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.48.2",
"unsloth_fixed": true,
"unsloth_version": "2025.1.8",
"use_cache": true,
"vocab_size": 128256
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

11
generation_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": 128001,
"max_length": 131072,
"pad_token_id": 128004,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.48.2"
}

BIN
maestro-r1-llama-loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 114 KiB

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4355717d204d5816fb10048ece876263b0c42ecfbb7bc09bff1e3e87c8c35ae7
size 4976698592

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3aa0fbc4bc8b925bb8ea56f83780628486e1993a666ddcb032fab8145b1991ca
size 4999802616

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09f350849e48c764c0a0f16b2542a29b5c773a5dd19148dc655e91db083deb45
size 4915916080

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:118020743d09bb23fdc1973f98bc71f494b92ea6ae07422b2d3f1a973ac64392
size 1168138808

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 16060522496
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

3
pytorch_model-00001-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c396e98e69c339b0bc7e7b3db8215ed853eff1f1eaa126197f6b7fbdb42698d
size 4976718466

3
pytorch_model-00002-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0dfd1152681d3908c04fd92b693006b2c2c3dd3e08367e22e15095196c2e08d2
size 4999827206

3
pytorch_model-00003-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:32215fb20be85a01d016d7d6960c3f4c5cd6bf6afa11d0413795bee690483f2d
size 4915939082

3
pytorch_model-00004-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:83c0da81eaf42630fcb2181da919bb665d58fb5ef3f5b390ccbdf2b466f5fb9d
size 1168140873

3
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9dbd847ac143506b53ff7fb4839101e826bf3e6ca41796607157d0893b62c852
size 23950

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<｜begin▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|finetune_right_pad_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
size 17209530

2068
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff