Upload folder using huggingface_hub

.gitattributes

@@ -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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,254 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-Medium-3.5-128B
+tags:
+- mistral
+- mistral-3.5
+- text-only
+- bf16
+- 128b
+---
+
+<style>
+body {
+  font-family: 'Quicksand', sans-serif;
+  background: linear-gradient(135deg, #4a1e00 0%, #1c0a00 100%);
+  color: #F5EFE6;
+  margin: 0;
+  padding: 0;
+  font-size: 16px;
+}
+
+h1, h2, h3, h4, summary {
+    font-family: 'Cinzel', serif;
+}
+
+.container {
+  margin: 20px auto;
+  max-width: 900px;
+  background-color: rgba(28, 22, 18, 0.95);
+  padding: 30px;
+  border-radius: 12px;
+  box-shadow: 0 4px 20px rgba(255, 140, 0, 0.15);
+  border: 1px solid rgba(255, 140, 0, 0.2);
+  outline: 1px solid rgba(255, 140, 0, 0.5);
+  outline-offset: -1px;
+  position: relative;
+}
+
+.container::before {
+  content: '';
+  position: absolute;
+  top: -1px;
+  left: -1px;
+  right: -1px;
+  bottom: -1px;
+  border: 1px solid rgba(255, 165, 0, 0.98);
+  border-radius: 12px;
+  pointer-events: none;
+  animation: borderGlow 2.5s ease-in-out infinite;
+}
+
+@keyframes borderGlow {
+  0% { box-shadow: 0 0 5px rgba(255, 165, 0, 0.98); }
+  50% { box-shadow: 0 0 12px rgba(255, 165, 0, 0.98); }
+  100% { box-shadow: 0 0 5px rgba(255, 165, 0, 0.98); }
+}
+
+.header h1 {
+  font-size: 32px;
+  color: #FFA500;
+  margin: 0 0 20px 0;
+  text-align: center;
+  text-shadow: 0 0 12px rgba(255, 100, 0, 0.6);
+}
+
+a {
+  color: #FFD700;
+  text-decoration: none;
+  transition: color 0.3s ease;
+}
+
+.button {
+  display: inline-block;
+  background-color: #E55B00;
+  color: #FFFFFF;
+  padding: 12px 24px;
+  border-radius: 5px;
+  cursor: pointer;
+  text-decoration: none;
+  font-family: 'Cinzel', serif;
+  font-weight: 600;
+  transition: all 0.3s ease;
+  border: 1px solid transparent;
+}
+
+.button:hover {
+  background-color: #FF8C00;
+  box-shadow: 0 0 15px rgba(255, 140, 0, 0.5);
+  transform: translateY(-2px);
+}
+
+.info-card {
+  background: rgba(45, 35, 25, 0.95);
+  border: 1px solid rgba(255, 140, 0, 0.2);
+  border-radius: 8px;
+  overflow: hidden;
+  margin-bottom: 25px;
+}
+
+.info-header {
+  background: rgba(255, 140, 0, 0.1);
+  padding: 20px;
+  border-bottom: 1px solid rgba(255, 140, 0, 0.2);
+}
+
+.info-header h3 {
+  color: #FFA500;
+  margin: 0 0 10px 0;
+  font-size: 22px;
+}
+
+.card-content {
+  padding: 20px;
+  line-height: 1.7;
+}
+
+.card-content ul {
+    list-style: none;
+    padding-left: 20px;
+}
+
+.card-content li::before {
+    content: '✦';
+    color: #FFD700;
+    font-weight: bold;
+    display: inline-block;
+    width: 1em;
+    margin-left: -1.2em;
+}
+
+.card-content strong {
+    color: #FFD700;
+}
+
+/* Update to the note card */
+.note-card {
+  border: 1px solid #FFA500;
+  box-shadow: 0 0 10px rgba(255, 165, 0, 0.1);
+}
+
+.note-header {
+  background: rgba(255, 165, 0, 0.1);
+}
+
+.note-header h3 {
+  color: #FFA500;
+  text-align: center;
+}
+
+.support-section {
+    text-align: center;
+    margin-top: 40px;
+    background: rgba(45, 35, 25, 0.95);
+    border: 1px solid rgba(255, 140, 0, 0.2);
+    border-radius: 8px;
+    padding: 20px;
+}
+
+summary {
+    cursor: pointer;
+    list-style: none;
+    outline: none;
+    display: flex;
+    align-items: center;
+}
+
+summary::before {
+    content: '▶';
+    font-size: 1.2em;
+    color: #FFA500;
+    margin-right: 15px;
+    transition: transform 0.2s ease;
+}
+
+details[open] > summary::before {
+    transform: rotate(90deg);
+}
+
+h2 {
+    color: #FFA500;
+    border-bottom: 1px solid rgba(255, 140, 0, 0.2);
+    padding-bottom: 10px;
+    margin-bottom: 20px;
+}
+</style>
+
+<div class="container">
+<link href="https://fonts.googleapis.com/css2?family=Cinzel:wght@400;500;600&family=Quicksand:wght@400;500&display=swap" rel="stylesheet">
+
+<div class="header">
+  <h1>Mistral-Medium-3.5-128B-BF16-Text-Only</h1>
+</div>
+
+<div class="info">
+  
+  <div class="info-card note-card">
+    <div class="info-header note-header">
+      <h3>📜 Technical Architecture Note</h3>
+    </div>
+    <div class="card-content">
+      <p>This model has been converted from <strong>Mistral3ForConditionalGeneration</strong> (Multimodal) to <strong>MistralForCausalLM</strong> (Standard Text-Only). This change ensures maximum compatibility with standard fine-tuning libraries like <em>Axolotl, Unsloth, and Hugging Face Transformers</em> without requiring custom vision-encoder handling.</p>
+    </div>
+  </div>
+
+  <div class="support-section">
+    <p><strong>Help me feed the data beast! Taking commissions for universe-specific models.</strong></p>
+    <a href="https://ko-fi.com/som1tokmynam" target="_blank" class="button">
+      Support on Ko-fi
+    </a>
+  </div>
+  
+  <div class="section-container">
+    <details open>
+      <summary><h2>Model Description</h2></summary>
+      <div class="info-card">
+        <div class="card-content">
+          <p>This is a processed version of <strong>Mistral-Medium-3.5-128B</strong> designed for users who prioritize text-only performance and ease of fine-tuning.</p>
+          <p><strong>Modification Details:</strong></p>
+          <ul>
+            <li><strong>Precision Upscale:</strong> Converted from <strong>FP8</strong> weights to <strong>BF16</strong> to restore full 16-bit brain-float precision for stable gradient updates during training.</li>
+            <li><strong>Vision Layer Stripping:</strong> All vision encoders and multimodal projection layers have been removed, significantly reducing memory overhead during inference and training for text-only tasks.</li>
+            <li><strong>Architecture Re-mapping:</strong> The configuration has been modified to use <code>MistralForCausalLM</code>, allowing it to be treated as a standard dense language model.</li>
+          </ul>
+        </div>
+      </div>
+    </details>
+  </div>
+
+  <div class="section-container">
+    <details>
+      <summary><h2>Purpose & Usage</h2></summary>
+      <div class="info-card">
+          <div class="card-content">
+              <p>This model is intended to serve as a <strong>clean base for fine-tuning</strong>. By removing the vision components, you can allocate more VRAM to sequence length or batch size. It is 100% functional for text-only chat and reasoning out of the box.</p>
+          </div>
+      </div>
+    </details>
+  </div>
+
+  <div class="section-container">
+    <details>
+      <summary><h2>Acknowledgements</h2></summary>
+      <div class="info-card">
+          <div class="card-content">
+              <ul>
+                  <li>Credit to <strong>Mistral AI</strong> for the original Mistral-Medium-3.5-128B architecture.</li>
+              </ul>
+          </div>
+      </div>
+    </details>
+  </div>
+
+</div>
+</div>

chat_template.jinja

@@ -0,0 +1,263 @@
+{#- Default date variables. To improve UX pass the correct ones to the Jinja render. #}
+{%- if today is not defined %}
+    {%- set today = '29-04-2026' %}
+{%- endif %}
+{%- if yesterday is not defined %}
+    {%- set yesterday = '28-04-2026' %}
+{%- endif %}
+
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message -%}
+You are Mistral Medium 3.5, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
+You are an intelligent conversational assistant powering an AI assistant called Le Chat.
+Your knowledge base was last updated on Friday, November 1, 2024.
+The current date is {{ today }}.
+
+# GENERAL GUIDELINES
+
+- Accurately answer the user's question.
+- For uncertain information or when the user's request requires up-to-date or specific data, use the available tools to fetch the information.
+- Be very attentive to dates, always try to resolve dates (e.g. "yesterday" is {{ yesterday }}) and when asked about information at specific dates, discard information that is at another date.
+
+# WEB BROWSING INSTRUCTIONS
+
+You cannot perform any web search or access internet to open URLs, links etc without dedicated tools.
+
+# MULTI-MODAL INSTRUCTIONS
+
+- You have the ability to read images.
+- You cannot read audio nor videos.
+- You cannot generate images without dedicated tools.
+
+# TOOL CALLING INSTRUCTIONS
+
+You may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:
+
+1. When the request requires up-to-date information.
+2. When the request requires specific data that you do not have in your knowledge base.
+3. When the request involves actions that you cannot perform without tools.
+
+Always prioritize using tools to provide the most accurate and helpful response.
+{%- endset %}
+
+{#- Begin of sequence token. #}
+{{- '<s>' }}
+
+
+{#- Handle system prompt if it exists. #}
+{%- set loop_messages = messages %}
+{%- if messages[0]['role'] != 'system' and default_system_message != '' %}
+    {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+{%- endif %}
+
+
+{#- Tools and model settings definition #}
+{%- set available_tools = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set available_tools = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+{%- endif %}
+{%- if reasoning_effort is not defined or reasoning_effort is none %}
+    {%- set reasoning_effort = 'none' %}
+{%- endif %}
+{%- if reasoning_effort not in ['none', 'high'] %}
+    {{- raise_exception('reasoning_effort must be either "none" or "high"') }}
+{%- endif %}
+{%- set model_settings = '[MODEL_SETTINGS]{"reasoning_effort": "' + reasoning_effort + '"}[/MODEL_SETTINGS]' %}
+
+{#- Aggregate consecutive messages with the same role except system and tool. #}
+{#- A sentinel message is appended so the last group gets flushed inside the loop. #}
+{%- set ns_agg = namespace(messages=[], current_group=[], current_role=none) %}
+{%- for message in loop_messages + [{'role': '__sentinel__'}] %}
+    {%- if message['role'] != ns_agg.current_role or message['role'] == 'system' or message['role'] == 'tool' %}
+        {%- if ns_agg.current_role == 'tool' %}
+            {%- set ns_agg.messages = ns_agg.messages + ns_agg.current_group %}
+        {%- elif ns_agg.current_role is not none %}
+            {%- set ns_c = namespace(text_parts=[], chunks=[], has_non_text=false, tool_calls=[]) %}
+            {%- for msg in ns_agg.current_group %}
+                {#- Convert reasoning / reasoning_content to a leading thinking chunk. #}
+                {%- set reasoning = msg.get('reasoning_content', msg.get('reasoning', none)) %}
+                {%- if reasoning is not none and reasoning != '' %}
+                    {%- set think_chunk = {'type': 'thinking', 'thinking': reasoning} %}
+                    {%- if msg['content'] is string and msg['content'] != '' %}
+                        {%- set new_content = [think_chunk, {'type': 'text', 'text': msg['content']}] %}
+                    {%- elif msg['content'] is not none and msg['content'] is not string and msg['content'] | length > 0 %}
+                        {%- set new_content = [think_chunk] + msg['content'] | list %}
+                    {%- else %}
+                        {%- set new_content = [think_chunk] %}
+                    {%- endif %}
+                    {%- if msg['tool_calls'] is defined and msg['tool_calls'] is not none %}
+                        {%- set msg = {'role': msg['role'], 'content': new_content, 'tool_calls': msg['tool_calls']} %}
+                    {%- else %}
+                        {%- set msg = {'role': msg['role'], 'content': new_content} %}
+                    {%- endif %}
+                {%- endif %}
+                {%- if msg['content'] is string %}
+                    {%- set ns_c.text_parts = ns_c.text_parts + [msg['content']] %}
+                {%- elif msg['content'] is not none %}
+                    {%- for block in msg['content'] %}
+                        {%- if block['type'] == 'text' %}
+                            {%- set ns_c.text_parts = ns_c.text_parts + [block['text']] %}
+                        {%- else %}
+                            {%- if ns_c.text_parts | length > 0 %}
+                                {%- set ns_c.chunks = ns_c.chunks + [{'type': 'text', 'text': ns_c.text_parts | join('\n\n')}] %}
+                                {%- set ns_c.text_parts = [] %}
+                            {%- endif %}
+                            {%- set ns_c.chunks = ns_c.chunks + [block] %}
+                            {%- set ns_c.has_non_text = true %}
+                        {%- endif %}
+                    {%- endfor %}
+                {%- endif %}
+                {%- if msg['tool_calls'] is defined and msg['tool_calls'] is not none %}
+                    {%- set ns_c.tool_calls = ns_c.tool_calls + msg['tool_calls'] | list %}
+                {%- endif %}
+            {%- endfor %}
+            {%- if ns_c.has_non_text %}
+                {%- if ns_c.text_parts | length > 0 %}
+                    {%- set ns_c.chunks = ns_c.chunks + [{'type': 'text', 'text': ns_c.text_parts | join('\n\n')}] %}
+                {%- endif %}
+                {%- set merged_content = ns_c.chunks %}
+            {%- else %}
+                {%- set merged_content = ns_c.text_parts | join('\n\n') %}
+            {%- endif %}
+            {%- if ns_c.tool_calls | length > 0 %}
+                {%- set ns_agg.messages = ns_agg.messages + [{'role': ns_agg.current_role, 'content': merged_content, 'tool_calls': ns_c.tool_calls}] %}
+            {%- else %}
+                {%- set ns_agg.messages = ns_agg.messages + [{'role': ns_agg.current_role, 'content': merged_content}] %}
+            {%- endif %}
+        {%- endif %}
+        {%- if message['role'] != '__sentinel__' %}
+            {%- set ns_agg.current_group = [message] %}
+            {%- set ns_agg.current_role = message['role'] %}
+        {%- endif %}
+    {%- else %}
+        {%- set ns_agg.current_group = ns_agg.current_group + [message] %}
+    {%- endif %}
+{%- endfor %}
+{%- set loop_messages = ns_agg.messages %}
+
+{#- Validates message ordering. #}
+{%- set ns = namespace(available_tools_and_settings_emitted=false) %}
+{%- if loop_messages | length > 0 and loop_messages[0]['role'] != 'user' and loop_messages[0]['role'] != 'system' %}
+    {{- raise_exception('Conversation must start with a user or system message, got ' + loop_messages[0]['role'] + '.') }}
+{%- endif %}
+{%- set ns_order = namespace(previous_role=none) %}
+{%- for message in loop_messages %}
+    {%- set current_role = message['role'] %}
+    {%- if ns_order.previous_role is not none %}
+        {%- if ns_order.previous_role == 'system' %}
+            {%- if current_role != 'user' and current_role != 'assistant' and current_role != 'system' %}
+                {{- raise_exception('Unexpected role \'' + current_role + '\' after role \'' + ns_order.previous_role + '\'') }}
+            {%- endif %}
+        {%- elif ns_order.previous_role == 'user' %}
+            {%- if current_role != 'assistant' and current_role != 'system' and current_role != 'user' %}
+                {{- raise_exception('Unexpected role \'' + current_role + '\' after role \'' + ns_order.previous_role + '\'') }}
+            {%- endif %}
+        {%- elif ns_order.previous_role == 'assistant' %}
+            {%- if current_role != 'assistant' and current_role != 'user' and current_role != 'tool' %}
+                {{- raise_exception('Unexpected role \'' + current_role + '\' after role \'' + ns_order.previous_role + '\'') }}
+            {%- endif %}
+        {%- elif ns_order.previous_role == 'tool' %}
+            {%- if current_role != 'assistant' and current_role != 'tool' and current_role != 'user' %}
+                {{- raise_exception('Unexpected role \'' + current_role + '\' after role \'' + ns_order.previous_role + '\'') }}
+            {%- endif %}
+        {%- endif %}
+    {%- endif %}
+    {%- set ns_order.previous_role = current_role %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+    {#- User messages supports text, image and image_url content. #}
+    {%- if message['role'] == 'user' %}
+        {%- if not ns.available_tools_and_settings_emitted %}
+            {{- available_tools }}
+            {{- model_settings }}
+            {%- set ns.available_tools_and_settings_emitted = true %}
+        {%- endif %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text and thinking content. #}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+            {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+        {%- endif %}
+
+        {%- if message['content'] is string and message['content'] != '' %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] == 'thinking' %}
+                    {{- '[THINK]' + block['thinking'] }}
+                    {%- if block.get('closed', true) %}{{- '[/THINK]' }}{%- endif %}
+                {%- else %}
+                    {{- raise_exception('Only text and thinking chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {{- '[TOOL_CALLS]' }}
+                {%- set name = tool['function']['name'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- name + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {{- '</s>' }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- System messages. #}
+    {%- elif message['role'] == 'system' %}
+        {{- '[SYSTEM_PROMPT]' -}}
+        {%- if message['content'] is string %}
+            {{- message['content'] -}}
+        {%- else %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in system message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '[/SYSTEM_PROMPT]' -}}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant, system and tool roles are supported, got ' + message['role'] + '.') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -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": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 262144,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "pad_token_id": 11,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 4.0,
+      "beta_slow": 1.0,
+      "factor": 64.0,
+      "llama_4_scaling_beta": 0,
+      "mscale": 1.0,
+      "mscale_all_dim": 0.0,
+      "original_max_position_embeddings": 4096,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

model-00000-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b254ec460ae5c73383ebfac95940ba3de5a61f7cbddf5e56b2ea4d7f4c7af00e
+size 5989467064

model-00001-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f498573b693ab9041a6d657734b4ebdc78b48f9450df3e956622f7f0589317ce
+size 5536581680

model-00002-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c875880ff390118d31447b3346fceb61fe41961323c617f053c5e6ae76a087
+size 5536581680

model-00003-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9cdcbdf7fd7ca05765982b5957e67243b10f9ca718ae8841b117d68d19e93b
+size 5536581680

model-00004-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a392d2dc54a2949f44e16c033ea09268d5afaa58329c30504d4d1474878ceed
+size 5536581680

model-00005-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47424d00b58c714553532cc859a89da326049dfd5983f78a20a925afec78fe3b
+size 5536581720

model-00006-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12632b715ae0455d36c83467e404a4ca6a7eaffd9c5257d1468c19920a0dba1
+size 5536581696

model-00007-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738a342e0c76e297170e9ff7e540199a58704af30d7a422a6dc66f59994aba1e
+size 5536581696

model-00008-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83477e1a05b647a5e1c7109b26b380af67826c86a32bfb305338bb25f1cb9bf4
+size 5536581696

model-00009-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291b2d7c96d9b11c7d588e0e338fbaa77295574d44686e5e77e0892396b17cfc
+size 5536581696

model-00010-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3825295c94eaa76fcb992fdf01d3d2042143170413c31b61e0e3a846e0fdcee0
+size 5536581696

model-00011-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62aa24afde4d399db3072e8d5316ce2bcc77c0d50dda710f43441e707a55c3ff
+size 5536581696

model-00012-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a19cd820c9bd9669e2e2b61ffb75223523b23b0bbcbcb5994ce1f0dea215d3
+size 5536581696

model-00013-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70d78b777d99128ebc5132053724f14e712ee91ead8a5761f061dd6a8e73a78
+size 5536581696

model-00014-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47af86e874607c2595e056f6769305b2faf02d4eac93f3a864b0741270c3c901
+size 5536581696

model-00015-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b22aacb84ed02d751a5e1ce515a5368ea8ea4bdc819c9be0e6ca240d30a4db9
+size 5536581696

model-00016-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6da1bcdc498716a8fe54e1993f4cf4180cc0075d808fcd2c8570b198dfa29d
+size 5536581696

model-00017-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20199bb7c57dd881f4b80b6ca457a236d6e61afffd3bc8c4e02a6e743c62e8f3
+size 5536581696

model-00018-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40be8b11e1094c896984e3c046691ac344fe5cdc35d5bf6d26682b729061c828
+size 5536581696

model-00019-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64c4780e7016184247cadab46260a12b4306266ee21267dadc3a16a4a00141d
+size 5536581696

model-00020-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3738e91cec42de47abba5ec96184a5a6c7d652f7128cf3587973c0356d6f9f41
+size 5536581696

model-00021-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9c1741b605d8e51f26b3c27c41b7d292366b15e7d70e7a6adac2cd88ffbd43
+size 5536581696

model-00022-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6044f32f457bb0e8857224ced81f9d67b7e09ac96aa9fda0a269d7350650137
+size 5536581696

model-00023-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288b1c486dfb979f76dfb94469af643d6ae44ec6764a8afdaee9c38e225713d1
+size 5536581696

model-00024-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24770888f17ea84b81c89a06ca2409d0732953babe671b1632af625b3b7d4518
+size 5536581696

model-00025-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2123ebf61b064537834a88382fb837ce2227ee8aa2c4d0a34617717f19a56b06
+size 5536581696

model-00026-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a0cd88d59f48be6d68c59d6205ceeac0fd6cf41f5863db963386fe1cb82ef4
+size 5536581696

model-00027-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3541774dbcc7b41bc47140a5012ff92bc12c8449c387def7afb073e040ce2f41
+size 5536581696

model-00028-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5810dae0bf2bfb0b61b5b937d7dad9c983c174e3838132b7f802bc4c68c4c27
+size 5536581696

model-00029-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed33e1c7753cf5240b160718188cc51db7b7b81e6f6b1514415275b1d1989acb
+size 5536581696

model-00030-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf48cbfd19e8cb3374d83d39875af1d2bf188f5efd6ccde42cdd162ca1c6a93
+size 5536581696

model-00031-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ddfccf58c79729b813af5c9f2450858ef4568c50b9a2c72a5b29f18b0b8f5f9
+size 5536581696

model-00032-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47924e4c2171c1ebdaac957e23003724f9f31c71911c674456ad0f562edfbd18
+size 5536581696

model-00033-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287100a58121068f64793c27d109d714c750f4fab2de690693ea17429d9ccd5e
+size 5536581696

model-00034-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781e6b5b9102af9b9c0df5792fbe8e3a37592c97a9a3df345fce88ed569ca417
+size 5536581696

model-00035-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494aa1c28c1fbb75fd0b9965e44a953337dad7e0ea87aac7ae192401478fb8ca
+size 5536581696

model-00036-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e6a66e44a683f489bab6088fc503b524a31c5031f4455bc7a7a66bd3765a1e
+size 5536581696

model-00037-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe441c273d7d914952d5740bfc37e0987b2abd363e54687b21c7f9aae8fd4078
+size 5536581696

model-00038-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b7457094c71d252a02ef658a67858dc98b8740a704290774d093cdbab88f07
+size 5536581696

model-00039-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf110381bc31c13674527a57bfd535927dba63d860693081ef786841c9db603
+size 5536581696

model-00040-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccdbaa8b2c4322b368d3e62946fe997a3adb1f7cf1a0baee1547bfb16e380cb
+size 5536581696

model-00041-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c38aae28147b7ed8ad95c4a57ed881ebbbe3d47f37e737206b38c370dbc742
+size 5536581696

model-00042-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3d241bea2b9b18b667d023202e68e01b5e262d2a4543a8da454781d24823b3
+size 5536581696

model-00043-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98743d5b9b0ce19e8a4087ec1c82c00734cdee483a4547de6d9b47393554891b
+size 5536581696

model-00044-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a965951421ee5ced9104dfbc1f31f7da443565c5536a99695563824a0c9782
+size 5989590496

model.safetensors.index.json

@@ -0,0 +1,802 @@
+{
+  "metadata": {
+    "total_size": 795
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00045.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00045.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00045.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00045.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00045.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00045.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00045.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00045.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00045.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00045.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00045.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00045.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00045.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00045.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00045.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00045.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00045.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00045.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00045.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00045.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00045.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00014-of-00045.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00045.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00015-of-00045.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00045.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00045.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00017-of-00045.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00018-of-00045.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00045.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00019-of-00045.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00020-of-00045.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00020-of-00045.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00021-of-00045.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00022-of-00045.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00022-of-00045.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00023-of-00045.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00024-of-00045.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00024-of-00045.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00025-of-00045.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00026-of-00045.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00026-of-00045.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00027-of-00045.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00028-of-00045.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00028-of-00045.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00029-of-00045.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00030-of-00045.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00030-of-00045.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00031-of-00045.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00032-of-00045.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00032-of-00045.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00033-of-00045.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00034-of-00045.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00034-of-00045.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00035-of-00045.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00036-of-00045.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00036-of-00045.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00037-of-00045.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00038-of-00045.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00038-of-00045.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00039-of-00045.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00040-of-00045.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.mlp.gate_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.self_attn.k_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.self_attn.o_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.self_attn.q_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.self_attn.v_proj.weight": "model-00040-of-00045.safetensors",
+    "model.layers.80.input_layernorm.weight": "model-00041-of-00045.safetensors",
+    "model.layers.80.post_attention_layernorm.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.input_layernorm.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.mlp.down_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.mlp.up_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.post_attention_layernorm.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.81.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.mlp.down_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.mlp.up_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
+    "model.layers.82.input_layernorm.weight": "model-00042-of-00045.safetensors",
+    "model.layers.82.post_attention_layernorm.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.input_layernorm.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.mlp.gate_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.post_attention_layernorm.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.self_attn.k_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.self_attn.o_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.self_attn.q_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.83.self_attn.v_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.mlp.gate_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.self_attn.k_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.self_attn.o_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.self_attn.q_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.self_attn.v_proj.weight": "model-00042-of-00045.safetensors",
+    "model.layers.84.input_layernorm.weight": "model-00043-of-00045.safetensors",
+    "model.layers.84.post_attention_layernorm.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.input_layernorm.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.mlp.down_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.mlp.up_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.post_attention_layernorm.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.85.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.mlp.down_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.mlp.up_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
+    "model.layers.86.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
+    "lm_head.weight": "model-00044-of-00045.safetensors",
+    "model.layers.86.input_layernorm.weight": "model-00044-of-00045.safetensors",
+    "model.layers.86.post_attention_layernorm.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.input_layernorm.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.mlp.down_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.mlp.gate_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.mlp.up_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.post_attention_layernorm.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.self_attn.k_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.self_attn.o_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.self_attn.q_proj.weight": "model-00044-of-00045.safetensors",
+    "model.layers.87.self_attn.v_proj.weight": "model-00044-of-00045.safetensors",
+    "model.norm.weight": "model-00044-of-00045.safetensors"
+  }
+}