ArtusDev commited on May 26

Commit

c74ab03

verified ·

1 Parent(s): 1cbf30e

Upload folder using huggingface_hub

Browse files

Files changed (22) hide show

.gitattributes +1 -0
README.md +415 -0
config.json +40 -0
generation_config.json +9 -0
latest +1 -0
measurement.json +0 -0
model.safetensors.index.json +460 -0
output.safetensors +3 -0
rng_state_0.pth +3 -0
rng_state_1.pth +3 -0
rng_state_2.pth +3 -0
rng_state_3.pth +3 -0
rng_state_4.pth +3 -0
rng_state_5.pth +3 -0
rng_state_6.pth +3 -0
rng_state_7.pth +3 -0
scheduler.pt +3 -0
special_tokens_map.json +30 -0
tokenizer.json +3 -0
tokenizer_config.json +0 -0
trainer_state.json +0 -0
zero_to_fp32.py +674 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,415 @@

+---
+datasets:
+- Delta-Vector/Hydrus-Instruct-SmolTalk-V2
+- Delta-Vector/Hydrus-SonnetOrca-V2
+- Delta-Vector/Hydrus-FeedSum-ShareGPT
+- Delta-Vector/Hydrus-Tulu-Personas-Filtered-Sharegpt
+- Delta-Vector/Hydrus-No_Robots-R1-Filtered
+- Delta-Vector/Hydrus-Chat_error-Pure-Dove-sharegpt
+- Delta-Vector/Hydrus-HelpSteer2
+- Delta-Vector/Hydrus-R1-Thinking-Sharegpt
+- Delta-Vector/Hydrus-Science-QA-sharegpt
+- Delta-Vector/Hydrus-Claude-Instruct-2.7K
+- Delta-Vector/Hydrus-Claude-Instruct-5K
+- PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4
+- PocketDoc/Dans-Toolmaxx-ShellCommands
+- PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
+- PocketDoc/Dans-Logicmaxx-SAT-AP
+- PocketDoc/Dans-Benchmaxx
+- Nitral-AI/ARES-ShareGPT
+- PocketDoc/Dans-Taskmaxx-TableGPT
+- Delta-Vector/Ursa-Erebus-16K
+- Delta-Vector/Ursa-Books-Light-Novels-V1
+- NewEden/Orion-LIT
+- Delta-Vector/Ursa-Asstr-V2-18k
+- Delta-Vector/Ursa-Books-V2
+- Delta-Vector/Ursa-Scribblehub-7k
+- Delta-Vector/Ursa-Orion-EA-Comp-Filtered
+- Delta-Vector/Ursa-HoneyFeed
+- Delta-Vector/Ursa-Falling-through-the-world
+base_model:
+- NewEden/Sol-Reaver-15B-Pretrain
+tags:
+- roleplay
+- instruct
+- creative_writing
+- story-writing
+- mistral
+---
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Sol-Reaver 15B</title>
+  <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
+  <style>
+    body {
+      font-family: 'Quicksand', sans-serif;
+      background: linear-gradient(135deg, #ffeef8 0%, #fff0e6 50%, #f8e8ff 100%);
+      color: #8b4a6b;
+      margin: 0;
+      padding: 0;
+      font-size: 16px;
+      min-height: 100vh;
+    }
+    .container {
+      margin: 20px;
+      background: linear-gradient(145deg, rgba(255, 255, 255, 0.9), rgba(255, 245, 250, 0.95));
+      padding: 30px;
+      border-radius: 20px;
+      box-shadow: 0 8px 32px rgba(255, 182, 193, 0.3), 0 4px 16px rgba(255, 215, 0, 0.2);
+      border: 2px solid rgba(255, 182, 193, 0.4);
+      position: relative;
+      backdrop-filter: blur(10px);
+    }
+    .container::before {
+      content: '';
+      position: absolute;
+      top: 0;
+      left: 0;
+      right: 0;
+      bottom: 0;
+      background: linear-gradient(45deg, rgba(255, 192, 203, 0.1), rgba(255, 215, 0, 0.1), rgba(221, 160, 221, 0.1));
+      border-radius: 20px;
+      z-index: -1;
+    }
+    .header h1 {
+      font-size: 32px;
+      background: linear-gradient(45deg, #d63384, #fd7e14, #e91e63);
+      -webkit-background-clip: text;
+      -webkit-text-fill-color: transparent;
+      background-clip: text;
+      margin: 0 0 20px 0;
+      text-align: center;
+      font-weight: 600;
+      text-shadow: 0 2px 4px rgba(255, 182, 193, 0.3);
+    }
+    .section {
+      margin-top: 30px;
+    }
+    .section h2 {
+      font-size: 24px;
+      background: linear-gradient(45deg, #d63384, #fd7e14);
+      -webkit-background-clip: text;
+      -webkit-text-fill-color: transparent;
+      background-clip: text;
+      text-align: center;
+      font-weight: 600;
+      margin-bottom: 20px;
+    }
+    .info p {
+      color: #8b4a6b;
+      line-height: 1.8;
+      font-size: 16px;
+    }
+    .info img {
+      width: 85%;
+      border-radius: 15px;
+      margin: 0 auto 15px;
+      display: block;
+      box-shadow: 0 8px 25px rgba(255, 182, 193, 0.4);
+      border: 2px solid rgba(255, 192, 203, 0.5);
+    }
+    a {
+      color: #d63384;
+      text-decoration: none;
+      transition: all 0.3s ease;
+      font-weight: 500;
+    }
+    a:hover {
+      color: #fd7e14;
+      text-shadow: 0 0 8px rgba(255, 215, 0, 0.6);
+    }
+    .button {
+      display: inline-block;
+      background: linear-gradient(45deg, #ffb6c1, #ffd700);
+      color: #8b4a6b;
+      padding: 12px 24px;
+      border-radius: 25px;
+      cursor: pointer;
+      text-decoration: none;
+      transition: all 0.3s ease;
+      border: 1px solid rgba(255, 182, 193, 0.5);
+      font-weight: 500;
+    }
+    .button:hover {
+      background: linear-gradient(45deg, #ff91a4, #ffed4e);
+      box-shadow: 0 4px 15px rgba(255, 182, 193, 0.6);
+      transform: translateY(-2px);
+    }
+    pre {
+      background: linear-gradient(135deg, rgba(255, 240, 245, 0.8), rgba(255, 248, 220, 0.8));
+      padding: 20px;
+      border-radius: 12px;
+      overflow-x: auto;
+      border: 1px solid rgba(255, 182, 193, 0.3);
+      box-shadow: inset 0 2px 4px rgba(255, 182, 193, 0.2);
+    }
+    code {
+      font-family: 'Courier New', monospace;
+      color: #8b4a6b;
+    }
+    .info-card {
+      background: linear-gradient(145deg, rgba(255, 240, 245, 0.9), rgba(255, 248, 220, 0.9));
+      border: 2px solid rgba(255, 182, 193, 0.4);
+      border-radius: 15px;
+      overflow: hidden;
+      box-shadow: 0 4px 20px rgba(255, 182, 193, 0.3);
+    }
+    .info-header {
+      background: linear-gradient(135deg, rgba(255, 192, 203, 0.3), rgba(255, 215, 0, 0.2));
+      padding: 25px;
+      border-bottom: 1px solid rgba(255, 182, 193, 0.3);
+    }
+    .info-header h3 {
+      background: linear-gradient(45deg, #d63384, #fd7e14);
+      -webkit-background-clip: text;
+      -webkit-text-fill-color: transparent;
+      background-clip: text;
+      margin: 0 0 15px 0;
+      font-size: 22px;
+      text-align: center;
+      font-weight: 600;
+    }
+    .model-tags {
+      display: flex;
+      gap: 10px;
+      flex-wrap: wrap;
+      justify-content: center;
+    }
+    .model-tag {
+      background: linear-gradient(45deg, rgba(255, 182, 193, 0.4), rgba(255, 215, 0, 0.3));
+      color: #8b4a6b;
+      padding: 8px 16px;
+      border-radius: 20px;
+      font-size: 13px;
+      border: 1px solid rgba(255, 182, 193, 0.5);
+      font-weight: 500;
+      box-shadow: 0 2px 8px rgba(255, 182, 193, 0.2);
+    }
+    .model-composition {
+      padding: 25px;
+      border-bottom: 1px solid rgba(255, 182, 193, 0.3);
+    }
+    .model-composition h4 {
+      background: linear-gradient(45deg, #d63384, #fd7e14);
+      -webkit-background-clip: text;
+      -webkit-text-fill-color: transparent;
+      background-clip: text;
+      margin: 0 0 20px 0;
+      font-size: 18px;
+      text-align: center;
+      font-weight: 600;
+    }
+    .composition-list {
+      list-style: none;
+      padding: 0;
+      margin: 0;
+      display: grid;
+      gap: 15px;
+    }
+    .composition-list li {
+      color: #8b4a6b;
+      display: flex;
+      align-items: baseline;
+      gap: 12px;
+      padding: 10px;
+      background: rgba(255, 240, 245, 0.5);
+      border-radius: 8px;
+      border-left: 4px solid #ffb6c1;
+    }
+    .model-component {
+      font-weight: 600;
+      min-width: 120px;
+    }
+    .model-description {
+      padding: 25px;
+      background: linear-gradient(135deg, rgba(255, 255, 255, 0.7), rgba(255, 240, 245, 0.8));
+    }
+    .metrics-section {
+      margin-bottom: 30px;
+    }
+    .metrics-section details {
+      background: linear-gradient(145deg, rgba(255, 240, 245, 0.9), rgba(255, 248, 220, 0.9));
+      border: 2px solid rgba(255, 182, 193, 0.4);
+      border-radius: 12px;
+      padding: 20px;
+      margin-bottom: 20px;
+      box-shadow: 0 4px 15px rgba(255, 182, 193, 0.2);
+    }
+    .metrics-section summary {
+      background: linear-gradient(45deg, #d63384, #fd7e14);
+      -webkit-background-clip: text;
+      -webkit-text-fill-color: transparent;
+      background-clip: text;
+      font-size: 18px;
+      cursor: pointer;
+      outline: none;
+      padding: 8px 0;
+      text-align: center;
+      font-weight: 600;
+      transition: all 0.3s ease;
+    }
+    .metrics-section summary:hover {
+      text-shadow: 0 0 8px rgba(255, 215, 0, 0.6);
+    }
+    .creator-section {
+      margin: 20px 0;
+      text-align: center;
+    }
+    .creator-badge {
+      display: inline-flex;
+      align-items: center;
+      background: linear-gradient(145deg, rgba(255, 240, 245, 0.9), rgba(255, 248, 220, 0.9));
+      border: 2px solid rgba(255, 182, 193, 0.4);
+      border-radius: 25px;
+      padding: 15px 20px;
+      box-shadow: 0 4px 15px rgba(255, 182, 193, 0.3);
+    }
+    .creator-label {
+      color: #8b4a6b;
+      font-size: 14px;
+      margin-right: 10px;
+      font-weight: 500;
+    }
+    .creator-link {
+      display: flex;
+      align-items: center;
+      gap: 8px;
+      color: #d63384;
+      text-decoration: none;
+      transition: all 0.3s ease;
+    }
+    .creator-name {
+      font-weight: 600;
+    }
+    .creator-arrow {
+      font-size: 16px;
+      transition: transform 0.3s ease;
+    }
+    .creator-link:hover .creator-arrow {
+      transform: translateX(4px);
+      color: #fd7e14;
+    }
+    .creator-link:hover {
+      color: #fd7e14;
+      text-shadow: 0 0 8px rgba(255, 215, 0, 0.6);
+    }
+    .link-arrow {
+      display: inline-block;
+      transition: transform 0.3s ease;
+    }
+    a:hover .link-arrow {
+      transform: translateX(3px);
+    }
+    .axolotl-container {
+      display: flex;
+      text-align: center; /* This is correctly applied to center the image itself */
+      justify-content: center;
+      margin: 30px 0;
+    }
+    .axolotl-container img {
+      max-width: 300px;
+      border-radius: 15px;
+      box-shadow: 0 6px 20px rgba(255, 182, 193, 0.4);
+      border: 2px solid rgba(255, 192, 203, 0.5);
+      transition: transform 0.3s ease;
+      display: block; /* Make the image a block element */
+      margin: 0 auto; /* Center it horizontally within its parent */
+    }
+    .axolotl-container img:hover {
+      transform: scale(1.05);
+    }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>Sol Reaver 15B</h1>
+    </div>
+    <div class="info">
+      <img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/DYgyLUEaHAv9kTffBYH-F.jpeg" alt="Model banner">
+      <div style="text-align: center;">
+      <div class="creator-section">
+        <div class="creator-badge">
+          <span class="creator-label">Created by</span>
+          <a href="https://huggingface.co/Delta-Vector" target="_blank" class="creator-link">
+            <span class="creator-name">Delta-Vector</span>
+            <span class="creator-arrow">→</span>
+          </a>
+        </div>
+      </div>
+      <div class="model-info">
+        <h2>Model Information</h2>
+        <div class="info-card">
+          <div class="info-header">
+            <h3>Sol-Reaver-15B-Instruct</h3>
+            <div class="model-tags">
+              <span class="model-tag">15B parameters</span>
+              <span class="model-tag">Creative / Fresh Prose</span>
+              <span class="model-tag">Co-writing/Roleplay/Adventure Generalist</span>
+            </div>
+          </div>
+          <div class="model-description">
+            <p>The first in the line of a New series of Roleplay / Adventure / Co-writer Models - Finetuned ontop of Sol-Reaver-15B-Pretrain</p>
+            <p>This model has been trained on 200M tokens of high quality Instruct data, It's focus is to provide a base for further finetuning|Merging</p>
+            <p>It's goal is to have refreshing Prose, Creativity, Good Instruct following and the *Brains*.</p>
+            <p>Support me on Ko-Fi: https://ko-fi.com/deltavector</p>
+          </div>
+        </div>
+      </div>
+      <div class="section">
+        <h2>Quantized Versions</h2>
+        <div class="info-card">
+          <div class="model-composition">
+            <h4>Available Downloads</h4>
+            <ul class="composition-list">
+              <li><span class="model-component"><a href="" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks(Coming Soon!)</li>
+              <li><span class="model-component"><a href="" target="_blank">EXL2 Format</a></span>For use with TabbyAPI (Coming Soon!)</li>
+              <li><span class="model-component"><a href="" target="_blank">EXL3 Format</a></span>For use with TabbyAPI (Slower on Ampere))</li>
+            </ul>
+          </div>
+        </div>
+      </div>
+      <div class="section">
+        <h2>Prompting</h2>
+        <p>Model has been tuned with the ChatML formatting. A typical input would look like this:</p>
+        <pre><code>&lt;|im_start|&gt;user
+Hi there!&lt;|im_end|&gt;
+&lt;|im_start|&gt;assistant
+Nice to meet you!&lt;|im_end|&gt;
+&lt;|im_start|&gt;user
+Can I ask a question?&lt;|im_end|&gt;
+&lt;|im_start|&gt;assistant
+</code></pre>
+      </div>
+      <div class="section">
+        <h2>Samplers</h2>
+        <p>For testing of this model, I used Temp=1, 0.1 Min-P.</p>
+        <div class="metrics-section">
+          <details>
+            <summary>See Axolotl Config</summary>
+            <pre><code>
+            https://files.catbox.moe/u9dakg.yml
+            </code></pre>
+          </details>
+        </div>
+      </div>
+     <div class="section">
+        <h2>Training</h2>
+        <p>The training was done for 2 epoch using 8 x <a href="https://www.nvidia.com/en-us/data-center/h200/">H200s</a> GPUs graciously provided by <a href="https://huggingface.co/kalomaze">Kalomaze</a> for the fine-tuning of the model.</p>
+        <div class="axolotl-container">
+          <a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
+            <img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">
+          </a>
+        </div>
+      </div>
+      <div class="section">
+        <h2>Credits</h2>
+        <p>Thank you to <a href="https://huggingface.co/lucyknada">Lucy Knada</a>, <a href="https://huggingface.co/Ateron">Ateron</a>, <a href="https://huggingface.co/AliCat2">Alicat</a>, <a href="https://huggingface.co/intervitens">Intervitens</a>, <a href="https://huggingface.co/cgato">Cgato</a>, <a href="https://huggingface.co/kubernetes-bad">Kubernetes Bad</a> and the rest of <a href="https://huggingface.co/anthracite-org">Anthracite</a>.</p>
+      </div>
+    </div>
+  </div>
+</body>
+</html>

config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 65536,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 50,
+    "num_key_value_heads": 8,
+    "pad_token_id": 10,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "unsloth_version": "2025.4.7",
+    "use_cache": false,
+    "vocab_size": 131072,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.3.0",
+        "bits": 2.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 65536,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.3"
+}

latest ADDED Viewed

	@@ -0,0 +1 @@


1	+ global_step848

measurement.json ADDED Viewed

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

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,460 @@

+{
+  "metadata": {
+    "total_size": 29948364800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

output.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c33216a85def27ef5bae64f3b77a27d136380fc2c3214802b6cddf1e4f2aaa1
+size 6134383976

rng_state_0.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2fbcd26bac3ea7dc02fc9ede5b8a1914ca51611473722a11a969e1f26ac0ee
+size 15984

rng_state_1.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:66d97b511d2fdb8061e5bf72c139923941c148260fac1caedd654028da6986c1
+size 15984

rng_state_2.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3839473129eb8c438ab312370daa55eb10a0790f33d38fc5eaa24859b54b0d1f
+size 15984

rng_state_3.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5088a0d34c7015afe60457fbb3f0a4740839369017a42ea4b3250322c2d63ceb
+size 15984

rng_state_4.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cac0eb25286b75549fa2030810940adf357064a83facaf5c58ebe37190b6ac
+size 15984

rng_state_5.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a57d29811122d52bd53f81af680412b91dde1cd2a12fa885d8a54388be8e2d
+size 15984

rng_state_6.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c90ab29b255eaf920ecc1cba0b586e426f8e2db67b44a65576693f84178a04f
+size 15984

rng_state_7.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4efbfa3cfb1bb8fb9c3380e65959a8b4eaf3bceb0507a26ffba1a3e4636ddb1
+size 15984

scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:faeb1a635984d135e9011d54b7e922d80780dc8bdc8698d280b304da2bb53b48
+size 1064

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:41c323e23875139dce13b6e6eeb3c31e2f1d259d590cee328ba4793bd8b053cc
+size 17078334

tokenizer_config.json ADDED Viewed

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

trainer_state.json ADDED Viewed

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

zero_to_fp32.py ADDED Viewed

	@@ -0,0 +1,674 @@

+#!/usr/bin/env python
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+# DeepSpeed Team
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+debug = 0
+# load to cpu
+device = torch.device('cpu')
+def atoi(text):
+    return int(text) if text.isdigit() else text
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+    return file
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+    return ckpt_files
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+        ds_version = state_dict.get(DS_VERSION, None)
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+    return zero_model_states
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+    if type(world_size) is list:
+        world_size = max(world_size)
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+    return zero_stage, world_size, fp32_flat_groups
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+    model_files = get_model_state_files(ds_checkpoint_dir)
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        state_dict[name] = frozen_param_fragments[name]
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+    return state_dict
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+    offset *= world_size
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+    return state_dict
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    Returns:
+        - pytorch ``state_dict``
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+    A typical usage might be ::
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    Returns:
+        - ``model`: modified model
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+    A typical usage might be ::
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+    return model
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+    debug = args.debug
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)