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

@@ -1,364 +1,330 @@
----
-base_model:
-- Vortex5/Cosmic-Night-12B
-base_model_relation: quantized
-pipeline_tag: text-generation
-library_name: safetensors
-tags:
-- exl3
-- 4-bit
-- 6-bit
-- 8-bit
----
-
-# Source model
-
-[**Cosmic-Night-12B**](https://huggingface.co/Vortex5/Cosmic-Night-12B) by [**Vortex5**](https://huggingface.co/Vortex5)
-
-------------------------------------------------------------------------------------------------------------------------
-
-## Provided quantized models
-
-[ExLlamaV3](https://github.com/turboderp-org/exllamav3): [**v0.0.29**](https://github.com/turboderp-org/exllamav3/releases/tag/v0.0.29)
-
-| Type | Size | CLI |
-|------|------|---------|
-| [H8-4.0BPW](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/tree/H8-4.0BPW) | 7.49 GB | [Copy-paste the lines / Download the batch file](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/resolve/H8-4.0BPW/Download~Vortex5_Cosmic-Night-12B_H8-4.0BPW_EXL3.bat) |
-| [H8-6.0BPW](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/tree/H8-6.0BPW) | 10.22 GB | [Copy-paste the lines / Download the batch file](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/resolve/H8-6.0BPW/Download~Vortex5_Cosmic-Night-12B_H8-6.0BPW_EXL3.bat) |
-| [H8-8.0BPW](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/tree/H8-8.0BPW) | 12.95 GB | [Copy-paste the lines / Download the batch file](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/resolve/H8-8.0BPW/Download~Vortex5_Cosmic-Night-12B_H8-8.0BPW_EXL3.bat) |
-
-***Requirements: A python installation with [huggingface-hub](https://huggingface.co/docs/huggingface_hub/main/en/guides/cli) module to use CLI.***
-
-### Licensing
-
-License detected: **apache-2.0**
-
-The license for the provided quantized models is inherited from the source model (which incorporates the license of its original base model). For definitive licensing information, please refer first to the page of the source or base models. File and page backups of the source model are provided below.
-
-------------------------------------------------------------------------------------------------------------------------
-
-# Backups
-
-Date: **19.04.2026**
-
-[Source files](https://huggingface.co/DeathGodlike/Vortex5_Cosmic-Night-12B_EXL3/tree/source-files)
-
-<details>
-<summary>Source page (click to expand)</summary>
-
-<section class="model-card">
-  <div class="header">
-    <h1 class="title">Cosmic-Night-12B</h1>
-  </div>
- 
-  <div class="image-container">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/6669a3a617b838fda45637b8/H9ivWbF1gbkxY-b-ZHjDs.jpeg">
-  </div>
-
-  <div class="divider"></div>
-
-  <section class="box">
-    <h2 class="box-title">Overview</h2>
-  <p>
-    <strong class="highlight">Cosmic-Night-12B</strong> was created by merging
-    <a href="https://huggingface.co/Vortex5/NoctyxCosma-12B" class="link">NoctyxCosma-12B</a>,
-    <a href="https://huggingface.co/TheDrummer/Rocinante-X-12B-v1" class="link">Rocinante-X-12B-v1</a>,
-    <a href="https://huggingface.co/anthracite-org/magnum-v4-12b" class="link">magnum-v4-12b</a>,
-    <a href="https://huggingface.co/crestf411/MN-Slush" class="link">MN-Slush</a>,
-    <a href="https://huggingface.co/Vortex5/Darklit-Maiden-12B" class="link">Darklit-Maiden-12B</a>,
-    <a href="https://huggingface.co/cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO" class="link">Nemo-12b-Humanize-SFT-v0.2.5-KTO</a>, and
-    <a href="https://huggingface.co/SuperbEmphasis/MN-12b-RP-Ink-RP-Longform" class="link">MN-12b-RP-Ink-RP-Longform</a>,
-    using a custom method.
-  </p>
-    <details class="collapse">
-      <summary>Merge configuration</summary>
-<pre>
-base_model: Vortex5/NoctyxCosma-12B
-models:
-  - model: TheDrummer/Rocinante-X-12B-v1
-  - model: anthracite-org/magnum-v4-12b
-  - model: crestf411/MN-Slush
-  - model: Vortex5/Darklit-Maiden-12B
-  - model: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO
-  - model: SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
-merge_method: gema
-chat_template: auto
-dtype: float32
-out_dtype: bfloat16
-parameters:
-  strength: 0.95
-  aggression: 0.89
-  consensus_amp: 1.52
-  novelty: 0.25
-  osmosis_strength: 0.92
-tokenizer:
-  source: Vortex5/NoctyxCosma-12B
-</pre>
-    </details>
-  </section>
-
-  <section class="box last-box">
-    <h2 class="box-title">Intended Use</h2>
-    <div class="grid">
-      <div class="tile">
-        <span class="tile-main">Roleplay</span>
-        <span class="tile-sub">Emotion-forward interaction</span>
-      </div>
-      <div class="tile">
-        <span class="tile-main">Storytelling</span>
-        <span class="tile-sub">Long-form narrative</span>
-      </div>
-      <div class="tile">
-        <span class="tile-main">Creative Writing</span>
-        <span class="tile-sub">Atmospheric fiction</span>
-      </div>
-    </div>
-  </section>
-
-  <div class="divider"></div>
-</section>
-
-<style>
-.model-card {
-  max-width: 1100px;
-  margin: 40px auto;
-  padding: 48px 38px 56px;
-  font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
-  color: #e8e8f5;
-  background:
-    radial-gradient(circle at 25% 30%, rgba(160, 180, 255, 0.10) 0%, transparent 50%),
-    radial-gradient(circle at 75% 65%, rgba(120, 140, 255, 0.08) 0%, transparent 55%),
-    #0c0c18;
-  border: 2px solid #4a4a6a;
-  border-radius: 28px;
-  position: relative;
-  overflow: hidden;
-}
-
-.model-card::before {
-  content: '';
-  position: absolute;
-  inset: 0;
-  background-image:
-    radial-gradient(circle, #ffffff 1.2px, transparent 1.2px),
-    radial-gradient(circle, #ffffff 1px, transparent 1px),
-
-    radial-gradient(circle, #d0d8ff 1.8px, transparent 1.8px),
-    radial-gradient(circle, #d0d8ff 1.4px, transparent 1.4px),
-
-    radial-gradient(circle, #a8b8ff 0.9px, transparent 0.9px),
-    radial-gradient(circle, #a8b8ff 0.7px, transparent 0.7px),
-    radial-gradient(circle, #e0e8ff 0.6px, transparent 0.6px);
-  background-position: 
-    0 0, 
-    28px 42px,
-    55px 15px,
-    80px 65px,
-    12px 88px,
-    95px 33px,
-    45px 78px;
-  background-size: 
-    85px 85px,
-    110px 95px,
-    70px 105px,
-    95px 80px,
-    60px 70px,
-    120px 55px,
-    75px 90px;
-  opacity: 0.22;
-  pointer-events: none;
-  z-index: 0;
-  animation: subtle-twinkle 24s linear infinite;
-}
-
-@keyframes subtle-twinkle {
-  0%, 100% { opacity: 0.22; }
-  50% { opacity: 0.29; }
-}
-
-.header {
-  text-align: center;
-  padding-bottom: 28px;
-  position: relative;
-  z-index: 1;
-}
-
-.title {
-  margin: 0;
-  font-size: clamp(1.75rem, 4.8vw, 2.85rem);
-  font-weight: 900;
-  letter-spacing: 0.14em;
-  text-transform: uppercase;
-  color: #f0f2ff;
-  text-shadow:
-    0 0 20px rgba(208, 212, 232, 0.5),
-    0 0 45px rgba(120, 140, 255, 0.35);
-}
-
-.image-container {
-  display: flex;
-  justify-content: center;
-  position: relative;
-  z-index: 1;
-  margin-bottom: 36px;
-}
-
-.image-container img {
-  width: 100%;
-  max-width: 820px;
-  border-radius: 22px;
-  border: 3px solid #5a5a7a;
-  box-shadow: 0 25px 60px -20px rgba(0, 0, 0, 0.7);
-}
-
-.divider {
-  height: 2px;
-  margin: 40px 0;
-  background: linear-gradient(90deg,
-    transparent,
-    #5a5a7a 25%,
-    #a0b8e0 50%,
-    #5a5a7a 75%,
-    transparent
-  );
-  position: relative;
-  z-index: 1;
-}
-
-.box {
-  padding: 34px;
-  background: rgba(26, 28, 48, 0.96);
-  border: 1px solid #4a4a6a;
-  border-radius: 20px;
-  box-shadow:
-    inset 0 4px 0 rgba(255,255,255,0.05),
-    0 15px 40px -15px rgba(0,0,0,0.6);
-  position: relative;
-  z-index: 2;
-  backdrop-filter: blur(10px);
-  margin-bottom: 32px;
-}
-
-.last-box {
-  margin-bottom: 0;
-}
-
-.box-title {
-  margin: 0 0 20px;
-  font-size: 1.18rem;
-  font-weight: 800;
-  letter-spacing: 0.22em;
-  text-transform: uppercase;
-  color: #d8dae8;
-  border-bottom: 2px solid #7a6eb0;
-  padding-bottom: 12px;
-  display: inline-block;
-}
-
-.box p {
-  margin: 16px 0 20px;
-  line-height: 1.8;
-  color: #c8cce0;
-  font-size: 1.04rem;
-}
-
-.highlight {
-  color: #f0f2ff;
-  font-weight: 700;
-  text-shadow: 0 0 8px rgba(160, 180, 255, 0.4);
-}
-
-.collapse {
-  margin-top: 24px;
-  background: rgba(20, 22, 40, 0.95);
-  border: 1px solid #5a5a7a;
-  border-radius: 16px;
-  overflow: hidden;
-}
-
-.collapse summary {
-  padding: 18px 24px;
-  cursor: pointer;
-  font-size: 0.85rem;
-  font-weight: 700;
-  letter-spacing: 0.15em;
-  text-transform: uppercase;
-  color: #e0e2f0;
-  background: rgba(35, 38, 58, 0.9);
-  border-bottom: 1px solid #4a4a6a;
-}
-
-.collapse pre {
-  margin: 0;
-  padding: 24px;
-  background: #161824;
-  color: #b8bcd8;
-  font-size: 0.87rem;
-  line-height: 1.7;
-  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
-  overflow-x: auto;
-}
-
-.grid {
-  display: flex;
-  flex-wrap: wrap;
-  gap: 24px;
-  margin-top: 20px;
-}
-
-.tile {
-  flex: 1 1 245px;
-  padding: 26px 22px;
-  background: rgba(28, 30, 52, 0.92);
-  border: 1px solid #5a5a7a;
-  border-radius: 18px;
-  text-align: center;
-  transition: all 0.4s cubic-bezier(0.23, 1, 0.32, 1);
-}
-
-.tile:hover {
-  transform: translateY(-6px);
-  border-color: #a0b8e0;
-  box-shadow: 0 20px 45px -15px rgba(160, 184, 224, 0.35);
-}
-
-.tile-main {
-  display: block;
-  margin-bottom: 10px;
-  font-size: 1.1rem;
-  font-weight: 800;
-  letter-spacing: 0.1em;
-  text-transform: uppercase;
-  color: #f0f2ff;
-}
-
-.tile-sub {
-  display: block;
-  font-size: 0.94rem;
-  color: #b0b4d0;
-  line-height: 1.5;
-}
-
-.link {
-  color: #a0b8e0;
-  text-decoration: none;
-  transition: color 0.3s ease;
-}
-
-.link:hover {
-  color: #e0e6ff;
-  text-decoration: underline;
-}
-
-@media (max-width: 650px) {
-  .model-card {
-    padding: 32px 20px 40px;
-    margin: 20px 10px;
-  }
-  .box {
-    padding: 26px;
-  }
-}
-</style>
-
-</details>
+---
+base_model:
+- anthracite-org/magnum-v4-12b
+- SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
+- Vortex5/Darklit-Maiden-12B
+- crestf411/MN-Slush
+- TheDrummer/Rocinante-X-12B-v1
+- cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO
+- Vortex5/NoctyxCosma-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- roleplay
+license: apache-2.0
+---
+<section class="model-card">
+  <div class="header">
+    <h1 class="title">Cosmic-Night-12B</h1>
+  </div>
+ 
+  <div class="image-container">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/6669a3a617b838fda45637b8/H9ivWbF1gbkxY-b-ZHjDs.jpeg">
+  </div>
+
+  <div class="divider"></div>
+
+  <section class="box">
+    <h2 class="box-title">Overview</h2>
+  <p>
+    <strong class="highlight">Cosmic-Night-12B</strong> was created by merging
+    <a href="https://huggingface.co/Vortex5/NoctyxCosma-12B" class="link">NoctyxCosma-12B</a>,
+    <a href="https://huggingface.co/TheDrummer/Rocinante-X-12B-v1" class="link">Rocinante-X-12B-v1</a>,
+    <a href="https://huggingface.co/anthracite-org/magnum-v4-12b" class="link">magnum-v4-12b</a>,
+    <a href="https://huggingface.co/crestf411/MN-Slush" class="link">MN-Slush</a>,
+    <a href="https://huggingface.co/Vortex5/Darklit-Maiden-12B" class="link">Darklit-Maiden-12B</a>,
+    <a href="https://huggingface.co/cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO" class="link">Nemo-12b-Humanize-SFT-v0.2.5-KTO</a>, and
+    <a href="https://huggingface.co/SuperbEmphasis/MN-12b-RP-Ink-RP-Longform" class="link">MN-12b-RP-Ink-RP-Longform</a>,
+    using a custom method.
+  </p>
+    <details class="collapse">
+      <summary>Merge configuration</summary>
+<pre>
+base_model: Vortex5/NoctyxCosma-12B
+models:
+  - model: TheDrummer/Rocinante-X-12B-v1
+  - model: anthracite-org/magnum-v4-12b
+  - model: crestf411/MN-Slush
+  - model: Vortex5/Darklit-Maiden-12B
+  - model: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO
+  - model: SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
+merge_method: gema
+chat_template: auto
+dtype: float32
+out_dtype: bfloat16
+parameters:
+  strength: 0.95
+  aggression: 0.89
+  consensus_amp: 1.52
+  novelty: 0.25
+  osmosis_strength: 0.92
+tokenizer:
+  source: Vortex5/NoctyxCosma-12B
+</pre>
+    </details>
+  </section>
+
+  <section class="box last-box">
+    <h2 class="box-title">Intended Use</h2>
+    <div class="grid">
+      <div class="tile">
+        <span class="tile-main">Roleplay</span>
+        <span class="tile-sub">Emotion-forward interaction</span>
+      </div>
+      <div class="tile">
+        <span class="tile-main">Storytelling</span>
+        <span class="tile-sub">Long-form narrative</span>
+      </div>
+      <div class="tile">
+        <span class="tile-main">Creative Writing</span>
+        <span class="tile-sub">Atmospheric fiction</span>
+      </div>
+    </div>
+  </section>
+
+  <div class="divider"></div>
+</section>
+
+<style>
+.model-card {
+  max-width: 1100px;
+  margin: 40px auto;
+  padding: 48px 38px 56px;
+  font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
+  color: #e8e8f5;
+  background:
+    radial-gradient(circle at 25% 30%, rgba(160, 180, 255, 0.10) 0%, transparent 50%),
+    radial-gradient(circle at 75% 65%, rgba(120, 140, 255, 0.08) 0%, transparent 55%),
+    #0c0c18;
+  border: 2px solid #4a4a6a;
+  border-radius: 28px;
+  position: relative;
+  overflow: hidden;
+}
+
+.model-card::before {
+  content: '';
+  position: absolute;
+  inset: 0;
+  background-image:
+    radial-gradient(circle, #ffffff 1.2px, transparent 1.2px),
+    radial-gradient(circle, #ffffff 1px, transparent 1px),
+
+    radial-gradient(circle, #d0d8ff 1.8px, transparent 1.8px),
+    radial-gradient(circle, #d0d8ff 1.4px, transparent 1.4px),
+
+    radial-gradient(circle, #a8b8ff 0.9px, transparent 0.9px),
+    radial-gradient(circle, #a8b8ff 0.7px, transparent 0.7px),
+    radial-gradient(circle, #e0e8ff 0.6px, transparent 0.6px);
+  background-position: 
+    0 0, 
+    28px 42px,
+    55px 15px,
+    80px 65px,
+    12px 88px,
+    95px 33px,
+    45px 78px;
+  background-size: 
+    85px 85px,
+    110px 95px,
+    70px 105px,
+    95px 80px,
+    60px 70px,
+    120px 55px,
+    75px 90px;
+  opacity: 0.22;
+  pointer-events: none;
+  z-index: 0;
+  animation: subtle-twinkle 24s linear infinite;
+}
+
+@keyframes subtle-twinkle {
+  0%, 100% { opacity: 0.22; }
+  50% { opacity: 0.29; }
+}
+
+.header {
+  text-align: center;
+  padding-bottom: 28px;
+  position: relative;
+  z-index: 1;
+}
+
+.title {
+  margin: 0;
+  font-size: clamp(1.75rem, 4.8vw, 2.85rem);
+  font-weight: 900;
+  letter-spacing: 0.14em;
+  text-transform: uppercase;
+  color: #f0f2ff;
+  text-shadow:
+    0 0 20px rgba(208, 212, 232, 0.5),
+    0 0 45px rgba(120, 140, 255, 0.35);
+}
+
+.image-container {
+  display: flex;
+  justify-content: center;
+  position: relative;
+  z-index: 1;
+  margin-bottom: 36px;
+}
+
+.image-container img {
+  width: 100%;
+  max-width: 820px;
+  border-radius: 22px;
+  border: 3px solid #5a5a7a;
+  box-shadow: 0 25px 60px -20px rgba(0, 0, 0, 0.7);
+}
+
+.divider {
+  height: 2px;
+  margin: 40px 0;
+  background: linear-gradient(90deg,
+    transparent,
+    #5a5a7a 25%,
+    #a0b8e0 50%,
+    #5a5a7a 75%,
+    transparent
+  );
+  position: relative;
+  z-index: 1;
+}
+
+.box {
+  padding: 34px;
+  background: rgba(26, 28, 48, 0.96);
+  border: 1px solid #4a4a6a;
+  border-radius: 20px;
+  box-shadow:
+    inset 0 4px 0 rgba(255,255,255,0.05),
+    0 15px 40px -15px rgba(0,0,0,0.6);
+  position: relative;
+  z-index: 2;
+  backdrop-filter: blur(10px);
+  margin-bottom: 32px;
+}
+
+.last-box {
+  margin-bottom: 0;
+}
+
+.box-title {
+  margin: 0 0 20px;
+  font-size: 1.18rem;
+  font-weight: 800;
+  letter-spacing: 0.22em;
+  text-transform: uppercase;
+  color: #d8dae8;
+  border-bottom: 2px solid #7a6eb0;
+  padding-bottom: 12px;
+  display: inline-block;
+}
+
+.box p {
+  margin: 16px 0 20px;
+  line-height: 1.8;
+  color: #c8cce0;
+  font-size: 1.04rem;
+}
+
+.highlight {
+  color: #f0f2ff;
+  font-weight: 700;
+  text-shadow: 0 0 8px rgba(160, 180, 255, 0.4);
+}
+
+.collapse {
+  margin-top: 24px;
+  background: rgba(20, 22, 40, 0.95);
+  border: 1px solid #5a5a7a;
+  border-radius: 16px;
+  overflow: hidden;
+}
+
+.collapse summary {
+  padding: 18px 24px;
+  cursor: pointer;
+  font-size: 0.85rem;
+  font-weight: 700;
+  letter-spacing: 0.15em;
+  text-transform: uppercase;
+  color: #e0e2f0;
+  background: rgba(35, 38, 58, 0.9);
+  border-bottom: 1px solid #4a4a6a;
+}
+
+.collapse pre {
+  margin: 0;
+  padding: 24px;
+  background: #161824;
+  color: #b8bcd8;
+  font-size: 0.87rem;
+  line-height: 1.7;
+  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
+  overflow-x: auto;
+}
+
+.grid {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 24px;
+  margin-top: 20px;
+}
+
+.tile {
+  flex: 1 1 245px;
+  padding: 26px 22px;
+  background: rgba(28, 30, 52, 0.92);
+  border: 1px solid #5a5a7a;
+  border-radius: 18px;
+  text-align: center;
+  transition: all 0.4s cubic-bezier(0.23, 1, 0.32, 1);
+}
+
+.tile:hover {
+  transform: translateY(-6px);
+  border-color: #a0b8e0;
+  box-shadow: 0 20px 45px -15px rgba(160, 184, 224, 0.35);
+}
+
+.tile-main {
+  display: block;
+  margin-bottom: 10px;
+  font-size: 1.1rem;
+  font-weight: 800;
+  letter-spacing: 0.1em;
+  text-transform: uppercase;
+  color: #f0f2ff;
+}
+
+.tile-sub {
+  display: block;
+  font-size: 0.94rem;
+  color: #b0b4d0;
+  line-height: 1.5;
+}
+
+.link {
+  color: #a0b8e0;
+  text-decoration: none;
+  transition: color 0.3s ease;
+}
+
+.link:hover {
+  color: #e0e6ff;
+  text-decoration: underline;
+}
+
+@media (max-width: 650px) {
+  .model-card {
+    padding: 32px 20px 40px;
+    margin: 20px 10px;
+  }
+  .box {
+    padding: 26px;
+  }
+}
+</style>

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS][" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST]" + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
+        {{- "[TOOL_CALLS][" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- message["content"] + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131075
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+base_model: Vortex5/NoctyxCosma-12B
+models:
+  - model: TheDrummer/Rocinante-X-12B-v1
+  - model: anthracite-org/magnum-v4-12b
+  - model: crestf411/MN-Slush
+  - model: Vortex5/Darklit-Maiden-12B
+  - model: cgato/Nemo-12b-Humanize-SFT-v0.2.5-KTO
+  - model: SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
+merge_method: gema
+chat_template: auto
+dtype: float32
+out_dtype: bfloat16
+parameters:
+  strength: 0.95
+  aggression: 0.89
+  consensus_amp: 1.52
+  novelty: 0.25
+  osmosis_strength: 0.92
+tokenizer:
+  source: Vortex5/NoctyxCosma-12B

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 24495626240,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33cb74e9ca1c0323b1be5f7e367b96bae218c22d0c4ed5b0edeec39f3a8755c3
+size 17078856