Upload folder using huggingface_hub

Browse files

Files changed (13) hide show

.gitattributes +1 -0
README.md +971 -0
config.json +37 -0
measurement.json +0 -0
mergekit_config.yml +8 -0
model.safetensors.index.json +1 -0
output-00001-of-00004.safetensors +3 -0
output-00002-of-00004.safetensors +3 -0
output-00003-of-00004.safetensors +3 -0
output-00004-of-00004.safetensors +3 -0
special_tokens_map.json +1032 -0
tokenizer.json +3 -0
tokenizer_config.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* 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

 *.zip 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

README.md ADDED Viewed

	@@ -0,0 +1,971 @@

+---
+base_model:
+- zerofata/MS3.2-PaintedFantasy-v2-24B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- axolotl
+license: apache-2.0
+datasets:
+- zerofata/Roleplay-Anime-Characters
+- zerofata/Instruct-Anime-CreativeWriting
+- zerofata/Instruct-Anime
+- zerofata/Summaries-Anime-FandomPages
+- zerofata/Stories-Anime
+---
+<style>
+.container {
+  --primary-accent: #EC83B1;
+  --secondary-accent: #86C5E5;
+  --tertiary-accent: #FDE484;
+  --accent-rose: #F8A5C2;
+  --bg-main: #1A1D2E;
+  --bg-container: #232741;
+  --bg-card: rgba(40, 45, 70, 0.7);
+  --text-main: #E8ECF0;
+  --text-muted: #B8C2D0;
+  --white: #FFFFFF;
+  --font-title: 'Inter', serif;
+  --font-heading: 'Inter', serif;
+  --font-body: 'Inter', serif;
+  --font-code: 'JetBrains Mono', monospace;
+  font-family: var(--font-body);
+  color: var(--text-main);
+  line-height: 1.6;
+  max-width: 1200px;
+  margin: 20px auto;
+  padding: 40px 20px;
+  background-color: var(--bg-container);
+  background-image:
+    radial-gradient(circle at 20% 80%, rgba(236, 131, 177, 0.04) 0%, transparent 50%),
+    radial-gradient(circle at 80% 20%, rgba(134, 197, 229, 0.04) 0%, transparent 50%),
+    radial-gradient(circle at 40% 40%, rgba(253, 228, 132, 0.02) 0%, transparent 50%);
+  min-height: calc(100vh - 40px);
+  border: 1px solid var(--primary-accent);
+  border-radius: 8px;
+  box-shadow: 0 8px 32px rgba(236, 131, 177, 0.07);
+}
+.container .title-container {
+  background-color: var(--bg-main);
+  position: relative;
+  overflow: hidden;
+  margin-bottom: 40px;
+  border-left: 3px solid var(--primary-accent);
+  box-shadow: 0 6px 20px rgba(236, 131, 177, 0.07);
+}
+.container .title-wrapper {
+  position: relative;
+  z-index: 2;
+  padding: 25px 20px 30px 30px;
+  font-family: var(--font-title);
+}
+.container .title-main {
+  color: var(--accent-rose);
+  font-size: 2.5rem;
+  font-weight: 700;
+  margin: 0;
+  letter-spacing: 2px;
+  display: inline-block;
+  position: relative;
+  text-transform: uppercase;
+}
+.container .title-prefix {
+  position: relative;
+  z-index: 2;
+}
+.container .lemonade-text {
+  color: var(--secondary-accent);
+  position: relative;
+  z-index: 2;
+  margin-left: 0.2em;
+  text-shadow: 0 0 15px var(--secondary-accent);
+}
+.container .title-subtitle {
+  padding-left: 15px;
+  margin-top: 5px;
+  margin-left: 5px;
+}
+.container .subtitle-text {
+  color: var(--text-muted);
+  font-size: 1.2rem;
+  font-family: var(--font-body);
+  font-weight: 300;
+  letter-spacing: 3px;
+  text-transform: uppercase;
+  display: inline-block;
+}
+.container .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(134, 197, 229, 0.08) 1px, rgba(0,0,0,0) 2px);
+  z-index: 1;
+}
+.container img {
+  max-width: 100%;
+  border: 3px solid var(--white);
+  margin-bottom: 30px;
+  box-shadow: 0 0 15px rgba(0, 0, 0, 0.3);
+}
+.container .section-container {
+  background-color: var(--bg-card);
+  margin-bottom: 30px;
+  position: relative;
+  overflow: hidden;
+  border-bottom: none !important;
+  box-shadow: 0 4px 15px rgba(236, 131, 177, 0.05);
+}
+.container .section-header {
+  display: flex;
+  align-items: center;
+  background-color: rgba(236, 131, 177, 0.12);
+  padding: 10px 20px;
+  border-bottom: none !important;
+}
+.container .section-indicator {
+  width: 8px;
+  height: 20px;
+  background-color: var(--primary-accent);
+  margin-right: 15px;
+  box-shadow: 0 0 8px rgba(236, 131, 177, 0.2);
+}
+.container .section-title {
+  font-family: var(--font-heading);
+  color: var(--accent-rose);
+  font-size: 1.4rem;
+  margin: 0 !important;
+  padding: 0 !important;
+  letter-spacing: 1px;
+  font-weight: 400;
+  text-transform: capitalize;
+  border-bottom: none !important;
+}
+.container .section-content {
+  padding: 20px;
+  font-family: var(--font-body);
+  color: var(--text-main);
+  line-height: 1.6;
+}
+.container .subheading {
+  color: var(--text-muted);
+  font-size: 1.1rem;
+  margin-top: 20px;
+  margin-bottom: 15px;
+  font-weight: 400;
+  border-bottom: 1px dashed rgba(184, 194, 208, 0.4);
+  display: inline-block;
+  text-transform: uppercase;
+  letter-spacing: 1px;
+  font-family: var(--font-heading);
+}
+.container .data-box {
+  background-color: rgba(26, 29, 46, 0.6);
+  padding: 15px;
+  border-left: 2px solid var(--primary-accent);
+  margin-bottom: 20px;
+  box-shadow: 0 2px 10px rgba(236, 131, 177, 0.05);
+}
+.container .data-row {
+  display: flex;
+  margin-bottom: 8px;
+  align-items: center;
+}
+.container .data-row:last-child { margin-bottom: 0; }
+.container .data-arrow {
+  color: var(--primary-accent);
+  width: 20px;
+  display: inline-block;
+}
+.container .data-label {
+  color: var(--text-muted);
+  width: 80px;
+  display: inline-block;
+}
+.container a {
+  color: var(--secondary-accent);
+  text-decoration: none;
+  font-weight: 600;
+  transition: color .3s;
+}
+.container a:hover {
+  text-decoration: underline;
+  color: var(--accent-rose);
+}
+.container .data-box a {
+  position: relative;
+  background-image: linear-gradient(to top, var(--primary-accent), var(--primary-accent));
+  background-position: 0 100%;
+  background-repeat: no-repeat;
+  background-size: 0% 2px;
+  transition: background-size .3s, color .3s;
+}
+.container .data-box a:hover {
+  color: var(--primary-accent);
+  background-size: 100% 2px;
+}
+.container .dropdown-container {
+  margin-top: 20px;
+}
+.container .dropdown-summary {
+  cursor: pointer;
+  padding: 10px 0;
+  border-bottom: 1px dashed rgba(184, 194, 208, 0.4);
+  color: var(--text-muted);
+  font-size: 1.1rem;
+  font-weight: 400;
+  text-transform: uppercase;
+  letter-spacing: 1px;
+  font-family: var(--font-heading);
+  list-style: none;
+  display: flex;
+  align-items: center;
+}
+.container .dropdown-summary::-webkit-details-marker {
+  display: none;
+}
+.container .dropdown-arrow {
+  color: var(--primary-accent);
+  margin-right: 10px;
+  transition: transform 0.3s ease;
+}
+.container details[open] .dropdown-arrow {
+  transform: rotate(90deg);
+}
+.container .dropdown-content {
+  margin-top: 15px;
+  padding: 15px;
+  background-color: rgba(26, 29, 46, 0.6);
+  border-left: 2px solid var(--primary-accent);
+  box-shadow: 0 2px 10px rgba(236, 131, 177, 0.05);
+}
+.container .config-title {
+  color: var(--text-muted);
+  font-size: 1rem;
+  margin-bottom: 10px;
+  font-family: var(--font-heading);
+  text-transform: uppercase;
+  letter-spacing: 1px;
+}
+.container pre {
+  background-color: var(--bg-main);
+  padding: 15px;
+  border: 1px solid rgba(134, 197, 229, 0.4);
+  white-space: pre-wrap;
+  word-wrap: break-word;
+  color: var(--text-main);
+  border-radius: 4px;
+}
+.container code {
+  font-family: var(--font-code);
+  background: transparent;
+  padding: 0;
+}
+</style>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Painted Fantasy</title>
+  <link rel="preconnect" href="https://fonts.googleapis.com">
+  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+  <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;600;700&family=JetBrains+Mono:wght@400;700&display=swap" rel="stylesheet">
+</head>
+<body>
+<div class="container">
+  <div class="title-container">
+    <div class="glitchy-overlay"></div>
+    <div class="title-wrapper">
+      <h1 class="title-main">
+        <span class="title-prefix">PAINTED FANTASY</span>
+        <span class="lemonade-text">VISAGE v2</span>
+      </h1>
+      <div class="title-subtitle">
+        <span class="subtitle-text">Mistrall Small 3.2 Upscaled 33B</span>
+      </div>
+    </div>
+  </div>
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/9FaT1DO7_b0B_sea1LiP7.png)
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">Overview</h2>
+    </div>
+    <div class="section-content">
+      <p>A surprisingly difficult model to work with. Removing the repetition was coming at the expense of the unique creativity the original upscale had.</p>
+      <p>Decided on upscaling Painted Fantasy v2, healing it and then merging the original upscale back in.</p>
+      <p>The result is a smarter, uncensored, creative model that excels at character driven RP / ERP where characters are portrayed creatively and proactively.</p>
+    </div>
+  </div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">SillyTavern Settings</h2>
+    </div>
+    <div class="section-content">
+      <h3 class="subheading">Recommended Roleplay Format</h3>
+      <div class="data-box">
+        <div class="data-row">
+            <span class="data-arrow">></span>
+            <span class="data-label">Actions:</span>
+            <span>In plaintext</span>
+        </div>
+      <div class="data-row">
+            <span class="data-arrow">></span>
+            <span class="data-label">Dialogue:</span>
+            <span>"In quotes"</span>
+      </div>
+      <div class="data-row">
+            <span class="data-arrow">></span>
+            <span class="data-label">Thoughts:</span>
+            <span>*In asterisks*</span>
+      </div>
+      </div>
+      <h3 class="subheading">Recommended Samplers</h3>
+      <div class="data-box">
+        <div class="data-row">
+          <span class="data-arrow">></span>
+          <span class="data-label">Temp:</span>
+          <span>0.6</span>
+        </div>
+        <div class="data-row">
+          <span class="data-arrow">></span>
+          <span class="data-label">MinP:</span>
+          <span>0.05 - 0.1</span>
+        </div>
+        <div class="data-row">
+          <span class="data-arrow">></span>
+          <span class="data-label">TopP:</span>
+          <span>0.9 - 1.0</span>
+        </div>
+        <div class="data-row">
+          <span class="data-arrow">></span>
+          <span class="data-label">Dry:</span>
+          <span>0.8, 1.75, 4</span>
+        </div>
+      </div>
+      <h3 class="subheading">Instruct</h3>
+      <div class="data-box">
+        <p style="margin: 0;">Mistral v7 Tekken</p>
+      </div>
+    </div>
+  </div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">Quantizations</h2>
+    </div>
+    <div class="section-content">
+      <div style="margin-bottom: 20px;">
+        <h3 class="subheading">GGUF</h3>
+        <div class="data-box">
+          <div class="data-row">
+            <span class="data-arrow">></span>
+            <a href="https://huggingface.co/bartowski/zerofata_MS3.2-PaintedFantasy-Visage-v2-33B-GGUF">iMatrix (bartowski)</a>
+          </div>
+        </div>
+      </div>
+      <div>
+        <h3 class="subheading">EXL3</h3>
+        <div class="data-box">
+          <div class="data-row">
+            <span class="data-arrow">></span>
+            <a href="https://huggingface.co/zerofata/MS3.2-PaintedFantasy-Visage-v2-33B-exl3-3bpw">3bpw</a>
+          </div>
+          <div class="data-row">
+            <span class="data-arrow">></span>
+            <a href="https://huggingface.co/zerofata/MS3.2-PaintedFantasy-Visage-v2-33B-exl3-4bpw">4bpw</a>
+          </div>
+          <div class="data-row">
+            <span class="data-arrow">></span>
+            <a href="https://huggingface.co/zerofata/MS3.2-PaintedFantasy-Visage-v2-33B-exl3-5bpw">5bpw</a>
+          </div>
+          <div class="data-row">
+            <span class="data-arrow">></span>
+            <a href="https://huggingface.co/zerofata/MS3.2-PaintedFantasy-Visage-v2-33B-exl3-6bpw">6bpw</a>
+          </div>
+        </div>
+      </div>
+    </div>
+  </div>
+  <div class="section-container">
+    <div class="section-header">
+      <div class="section-indicator"></div>
+      <h2 class="section-title">Creation Process</h2>
+    </div>
+    <div class="section-content">
+      <p>Creation Process: Upscale > PT > SFT > KTO > DPO</p>
+      <p>Pretrained on approx 300MB of light novels, stories and FineWeb-2 corpus.</p>
+      <p>SFT on approx 8 million tokens, SFW / NSFW RP, stories and creative instruct data.</p>
+      <p>KTO on antirep data created from the SFT datasets. Rejected examples generated by MS3.2 with repetition_penalty=0.9 and OOC commands encouraging it to misgender, impersonate user etc.</p>
+      <p>DPO on a high quality RP / NSFW dataset that is unreleased using rejected samples created in the same method as KTO.</p>
+      <p>Resulting model was non repetitive, but had lost some of the spark the original upscale had. Merged the original upscale back in, making sure to not reintroduce repetition.</p>
+              <div class="dropdown-container">
+          <details>
+            <summary class="dropdown-summary">
+              <span class="dropdown-arrow">></span>
+              Mergekit configs
+            </summary>
+            <div class="dropdown-content">
+              <p>Merge configurations used during the model creation process.</p>
+              <div class="config-title">Initial Upscale (Passthrough)</div>
+              <pre><code>base_model: zerofata/MS3.2-PaintedFantasy-v2-24B
+<br>
+merge_method: passthrough
+<br>
+dtype: bfloat16
+slices:
+  - sources:
+      - model: zerofata/MS3.2-PaintedFantasy-v2-24B
+        layer_range: [0, 29]
+  - sources:
+      - model: zerofata/MS3.2-PaintedFantasy-v2-24B
+        layer_range: [10, 39]</code></pre>
+              <div class="config-title">Final Merge (Slerp)</div>
+              <pre><code>models:
+  - model: zerofata/MS3.2-PaintedFantasy-Visage-33B
+  - model: ../axolotl/Visage-V2-PT-1-SFT-2-KTO-1-DPO-1/merged
+merge_method: slerp
+base_model: ../axolotl/Visage-V2-PT-1-SFT-2-KTO-1-DPO-1/merged
+parameters:
+  t: [0.4, 0.2, 0, 0.2, 0.4]
+dtype: bfloat16</code></pre>
+            </div>
+          </details>
+        </div>
+        <div class="dropdown-container">
+          <details>
+            <summary class="dropdown-summary">
+              <span class="dropdown-arrow">></span>
+              Axolotl configs
+            </summary>
+          <div class="dropdown-content">
+            <p>Not optimized for cost / performance efficiency, YMMV.</p>
+            <div class="config-title">Pretrain 4*H100</div>
+            <pre><code>&#35; ====================
+&#35; MODEL CONFIGURATION
+&#35; ====================
+base_model: ../mergekit/pf_v2_upscale
+model_type: MistralForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: mistral_v7_tekken
+&#35; ====================
+&#35; DATASET CONFIGURATION
+&#35; ====================
+datasets:
+  - path: ./data/pretrain_dataset_v5_stripped.jsonl
+    type: completion
+<br>
+dataset_prepared_path:
+train_on_inputs: false  &#35; Only train on assistant responses
+<br>
+&#35; ====================
+&#35; QLORA CONFIGURATION
+&#35; ====================
+adapter: qlora
+load_in_4bit: true
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+&#35; lora_modules_to_save:  &#35; Uncomment only if you added NEW tokens
+<br>
+&#35; ====================
+&#35; TRAINING PARAMETERS
+&#35; ====================
+num_epochs: 1
+micro_batch_size: 4
+gradient_accumulation_steps: 1
+learning_rate: 4e-5
+optimizer: paged_adamw_8bit
+lr_scheduler: rex
+warmup_ratio: 0.05
+weight_decay: 0.01
+max_grad_norm: 1.0
+<br>
+&#35; ====================
+&#35; SEQUENCE &amp; PACKING
+&#35; ====================
+sequence_len: 12288
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+<br>
+&#35; ====================
+&#35; HARDWARE OPTIMIZATIONS
+&#35; ====================
+bf16: auto
+flash_attention: true
+gradient_checkpointing: offload
+deepspeed: deepspeed_configs/zero1.json
+<br>
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+cut_cross_entropy: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+liger_fused_linear_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+<br>
+&#35; ====================
+&#35; EVALUATION &amp; CHECKPOINTING
+&#35; ====================
+save_strategy: steps
+save_steps: 40
+save_total_limit: 5  &#35; Keep best + last few checkpoints
+load_best_model_at_end: true
+greater_is_better: false
+<br>
+&#35; ====================
+&#35; LOGGING &amp; OUTPUT
+&#35; ====================
+output_dir: ./Visage-V2-PT-1
+logging_steps: 2
+save_safetensors: true
+<br>
+&#35; ====================
+&#35; WANDB TRACKING
+&#35; ====================
+wandb_project: Visage-V2-PT
+&#35; wandb_entity: your_entity
+wandb_name: Visage-V2-PT-1</code></pre>
+            <div class="config-title">SFT 4*H100</div>
+            <pre><code>&#35; ====================
+&#35; MODEL CONFIGURATION
+&#35; ====================
+base_model: ./Visage-V2-PT-1/merged
+model_type: MistralForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: mistral_v7_tekken
+<br>
+&#35; ====================
+&#35; DATASET CONFIGURATION
+&#35; ====================
+datasets:
+  - path: ./data/automated_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/handcrafted_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/instruct_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/cw_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/stories_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/cw_claude_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+  - path: ./data/summaries_dataset.jsonl
+    type: chat_template
+    split: train
+    chat_template_strategy: tokenizer
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      user: ["user"]
+      assistant: ["assistant"]
+      system: ["system"]
+<br>
+dataset_prepared_path:
+train_on_inputs: false  &#35; Only train on assistant responses
+<br>
+&#35; ====================
+&#35; QLORA CONFIGURATION
+&#35; ====================
+adapter: qlora
+load_in_4bit: true
+lora_r: 128
+lora_alpha: 128
+lora_dropout: 0.1
+lora_target_linear: true
+&#35; lora_modules_to_save:  &#35; Uncomment only if you added NEW tokens
+<br>
+&#35; ====================
+&#35; TRAINING PARAMETERS
+&#35; ====================
+num_epochs: 2
+micro_batch_size: 2
+gradient_accumulation_steps: 1
+learning_rate: 1e-5
+optimizer: paged_adamw_8bit
+lr_scheduler: rex
+warmup_ratio: 0.05
+weight_decay: 0.01
+max_grad_norm: 1.0
+<br>
+&#35; ====================
+&#35; SEQUENCE &amp; PACKING
+&#35; ====================
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+<br>
+&#35; ====================
+&#35; HARDWARE OPTIMIZATIONS
+&#35; ====================
+bf16: auto
+flash_attention: true
+gradient_checkpointing: offload
+deepspeed: deepspeed_configs/zero1.json
+<br>
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+cut_cross_entropy: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+liger_fused_linear_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+<br>
+<br>
+&#35; ====================
+&#35; EVALUATION &amp; CHECKPOINTING
+&#35; ====================
+save_strategy: steps
+save_steps: 20
+save_total_limit: 5  &#35; Keep best + last few checkpoints
+load_best_model_at_end: true
+metric_for_best_model: eval_loss
+greater_is_better: false
+<br>
+&#35; ====================
+&#35; LOGGING &amp; OUTPUT
+&#35; ====================
+output_dir: ./Visage-V2-PT-1-SFT-2
+logging_steps: 2
+save_safetensors: true
+<br>
+&#35; ====================
+&#35; WANDB TRACKING
+&#35; ====================
+wandb_project: Visage-V2-SFT
+&#35; wandb_entity: your_entity
+wandb_name: Visage-V2-PT-1-SFT-2</code></pre>
+            <div class="config-title">KTO 4*H100</div>
+            <pre><code>&#35; ====================
+&#35; MODEL CONFIGURATION
+&#35; ====================
+base_model: ./Visage-V2-PT-1-SFT-2/merged
+model_type: MistralForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: mistral_v7_tekken
+<br>
+&#35; ====================
+&#35; RL/DPO CONFIGURATION
+&#35; ====================
+rl: kto
+rl_beta: 0.1
+kto_desirable_weight: 1.25
+kto_undesirable_weight: 1.0
+<br>
+&#35; ====================
+&#35; DATASET CONFIGURATION
+&#35; ====================
+datasets:
+  - path: ./handcrafted_dataset_kto.jsonl
+    type: llama3.argilla
+  - path: ./approved_rp_dataset_kto.jsonl
+    type: llama3.argilla
+  - path: ./instruct_dataset_kto.jsonl
+    type: llama3.argilla
+dataset_prepared_path:
+train_on_inputs: false  &#35; Only train on assistant responses
+remove_unused_columns: False
+<br>
+&#35; ====================
+&#35; QLORA CONFIGURATION
+&#35; ====================
+adapter: qlora
+load_in_4bit: true
+lora_r: 32
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+&#35; lora_modules_to_save:  &#35; Uncomment only if you added NEW tokens
+<br>
+&#35; ====================
+&#35; TRAINING PARAMETERS
+&#35; ====================
+num_epochs: 1
+micro_batch_size: 4
+gradient_accumulation_steps: 4
+learning_rate: 5e-6
+optimizer: adamw_8bit
+lr_scheduler: cosine
+warmup_steps: 15
+weight_decay: 0.001
+max_grad_norm: 0.01
+<br>
+&#35; ====================
+&#35; SEQUENCE CONFIGURATION
+&#35; ====================
+sequence_len: 8192
+pad_to_sequence_len: true
+<br>
+&#35; ====================
+&#35; HARDWARE OPTIMIZATIONS
+&#35; ====================
+bf16: auto
+tf32: false
+flash_attention: true
+gradient_checkpointing: offload
+deepspeed: deepspeed_configs/zero1.json
+<br>
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+cut_cross_entropy: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+liger_fused_linear_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+<br>
+&#35; ====================
+&#35; CHECKPOINTING
+&#35; ====================
+save_steps: 100
+save_total_limit: 10
+load_best_model_at_end: true
+metric_for_best_model: eval_loss
+greater_is_better: false
+<br>
+&#35; ====================
+&#35; LOGGING &amp; OUTPUT
+&#35; ====================
+output_dir: ./Visage-V2-PT-1-SFT-2-KTO-1
+logging_steps: 2
+save_safetensors: true
+<br>
+&#35; ====================
+&#35; WANDB TRACKING
+&#35; ====================
+wandb_project: Visage-V2-KTO
+&#35; wandb_entity: your_entity
+wandb_name: Visage-V2-PT-1-SFT-2-KTO-1</code></pre>
+            <div class="config-title">DPO 4*H100</div>
+            <pre><code>&#35; ====================
+&#35; MODEL CONFIGURATION
+&#35; ====================
+base_model: ./Visage-V2-PT-1-SFT-2/merged
+model_type: MistralForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: mistral_v7_tekken
+<br>
+&#35; ====================
+&#35; RL/DPO CONFIGURATION
+&#35; ====================
+rl: dpo
+rl_beta: 0.1
+<br>
+&#35; ====================
+&#35; DATASET CONFIGURATION
+&#35; ====================
+datasets:
+  - path: ./handcrafted_dataset_mistral_rep.jsonl
+    type: chat_template.default
+    field_messages: messages
+    field_chosen: chosen
+    field_rejected: rejected
+    message_property_mappings:
+      role: role
+      content: content
+    roles:
+      system: ["system"]
+      user: ["user"]
+      assistant: ["assistant"]
+dataset_prepared_path:
+train_on_inputs: false  &#35; Only train on assistant responses
+<br>
+&#35; ====================
+&#35; QLORA CONFIGURATION
+&#35; ====================
+adapter: qlora
+load_in_4bit: true
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.1
+lora_target_linear: true
+&#35; lora_modules_to_save:  &#35; Uncomment only if you added NEW tokens
+<br>
+&#35; ====================
+&#35; TRAINING PARAMETERS
+&#35; ====================
+num_epochs: 1
+micro_batch_size: 2
+gradient_accumulation_steps: 1
+learning_rate: 2e-6
+optimizer: adamw_8bit
+lr_scheduler: cosine
+warmup_steps: 5
+weight_decay: 0.01
+max_grad_norm: 1.0
+<br>
+&#35; ====================
+&#35; SEQUENCE CONFIGURATION
+&#35; ====================
+sequence_len: 8192
+pad_to_sequence_len: true
+<br>
+&#35; ====================
+&#35; HARDWARE OPTIMIZATIONS
+&#35; ====================
+bf16: auto
+tf32: false
+flash_attention: true
+gradient_checkpointing: offload
+deepspeed: deepspeed_configs/zero1.json
+<br>
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+cut_cross_entropy: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+liger_fused_linear_cross_entropy: false  &#35; Cut Cross Entropy overrides this
+<br>
+&#35; ====================
+&#35; CHECKPOINTING
+&#35; ====================
+save_steps: 10
+save_total_limit: 10
+load_best_model_at_end: true
+metric_for_best_model: eval_loss
+greater_is_better: false
+<br>
+&#35; ====================
+&#35; LOGGING &amp; OUTPUT
+&#35; ====================
+output_dir: ./Visage-V2-PT-1-SFT-2-DPO-1
+logging_steps: 2
+save_safetensors: true
+<br>
+&#35; ====================
+&#35; WANDB TRACKING
+&#35; ====================
+wandb_project: Visage-V2-DPO
+&#35; wandb_entity: your_entity
+wandb_name: Visage-V2-PT-1-SFT-2-DPO-1</code></pre>
+          </div>
+        </details>
+      </div>
+    </div>
+  </div>
+</div>
+</body>
+</html>

config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 58,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.1",
+    "use_cache": true,
+    "vocab_size": 131072,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.3.1",
+        "bits": 6.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

measurement.json ADDED Viewed

The diff for this file is too large to render. See raw diff

mergekit_config.yml ADDED Viewed

	@@ -0,0 +1,8 @@

+models:
+  - model: zerofata/MS3.2-PaintedFantasy-Visage-33B
+  - model: ../axolotl/Visage-V2-PT-1-SFT-2-KTO-1-DPO-1/merged
+merge_method: slerp
+base_model: ../axolotl/Visage-V2-PT-1-SFT-2-KTO-1-DPO-1/merged
+parameters:
+  t: [0.4, 0.2, 0, 0.2, 0.4]
+dtype: bfloat16

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

output-00001-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd0cc62aea13f26c16184cbf8ddd75fd177abcda409bb59b6a5f06262559a23
+size 8468517088

output-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:776e4d84f0fb5fc41578c9373c17cccaa87a1771e05abbf3a9c90e87204aeeb4
+size 8565770074

output-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad1dc5b7b7dbc01f5948dc38dbb2fd7a72b6c1d0235f1fc978b0cb741ab05cd
+size 8486756066

output-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8346d47a762febf2bf123fc714e69ac9078429b22103949b3b3627dc1660d2
+size 528482400

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,1032 @@

+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "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
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

tokenizer_config.json ADDED Viewed

The diff for this file is too large to render. See raw diff