初始化项目，由ModelHub XC社区提供模型

Model: Vortex5/Azure-Starlight-12B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,256 @@
+---
+base_model:
+- Vortex5/Astral-Noctra-12B
+- Vortex5/Starlit-Shadow-12B
+- DreadPoor/Famino-12B-Model_Stock
+- Vortex5/Crimson-Twilight-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- roleplay
+license: apache-2.0
+---
+<section class="container">
+
+  <div class="header">
+    <h1 class="title">Azure-Starlight-12B</h1>
+  </div>
+
+  <div class="image-box">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/6669a3a617b838fda45637b8/srlvZGNLBPaI5vEOD0hNy.png">
+  </div>
+
+  <div class="divider"></div>
+
+  <section class="card">
+    <h2 class="card-title">Overview</h2>
+    <p>
+      <strong class="highlight">Azure-Starlight-12B</strong> was created by merging
+      <a href="https://huggingface.co/Vortex5/Astral-Noctra-12B" class="link">Astral-Noctra-12B</a>,
+      <a href="https://huggingface.co/Vortex5/Starlit-Shadow-12B" class="link">Starlit-Shadow-12B</a>,
+      <a href="https://huggingface.co/DreadPoor/Famino-12B-Model_Stock" class="link">Famino-12B-Model_Stock</a>, and
+	  <a href="https://huggingface.co/Vortex5/Crimson-Twilight-12B" class="link">Crimson-Twilight-12B</a> using the <a href="https://arxiv.org/abs/2403.19522" class="link">Model Stock</a> method.
+    </p>
+
+  <details class="config">
+      <summary>Merge Configuration</summary>
+      <pre>
+base_model: Vortex5/Astral-Noctra-12B
+models:
+  - model: Vortex5/Starlit-Shadow-12B
+  - model: DreadPoor/Famino-12B-Model_Stock
+  - model: Vortex5/Crimson-Twilight-12B
+  - model: Vortex5/Astral-Noctra-12B
+merge_method: model_stock
+chat_template: auto
+parameters:
+  normalize: true
+dtype: float32
+out_dtype: bfloat16
+tokenizer:
+  source: Vortex5/Astral-Noctra-12B
+      </pre>
+    </details>
+  </section>
+
+  <section class="card">
+    <h2 class="card-title">Intended Use</h2>
+    <div class="grid">
+      <div class="tile">
+        <span class="tile-main">Storytelling</span>
+        <span class="tile-sub">Structured long-form narrative</span>
+      </div>
+      <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">Creative Writing</span>
+        <span class="tile-sub">Atmospheric fiction</span>
+      </div>
+    </div>
+  </section>
+
+  <div class="divider"></div>
+
+</section>
+
+<style>
+
+.container{
+  --bg:#07121a;
+  --panel:#0f1f2a;
+  --glass:rgba(255,255,255,0.04);
+  --text:#e8f6ff;
+  --text-soft:rgba(232,246,255,0.65);
+  --accent:#00c2ff;
+  --accent2:#6fffe9;
+  --grad:linear-gradient(90deg,#00c2ff,#6fffe9,#b4f8ff);
+
+  max-width:1100px;
+  margin:50px auto;
+  padding:48px 50px;
+  border-radius:22px;
+  background:
+    radial-gradient(circle at 20% 10%, rgba(0,194,255,0.15), transparent 40%),
+    radial-gradient(circle at 80% 90%, rgba(111,255,233,0.12), transparent 50%),
+    var(--bg);
+  color:var(--text);
+  font-family:"Inter","Segoe UI",sans-serif;
+  display:flex;
+  flex-direction:column;
+  gap:40px;
+}
+
+.header{
+  text-align:center;
+  border-bottom:1px solid rgba(255,255,255,0.08);
+  padding-bottom:16px;
+}
+
+.title{
+  margin:0;
+  font-size:clamp(1.8rem,4.5vw,3rem);
+  line-height:1.2;
+  padding-bottom:4px;
+  font-weight:700;
+  letter-spacing:.05em;
+  background:var(--grad);
+  -webkit-background-clip:text;
+  background-clip:text;
+  color:transparent;
+}
+
+.image-box{
+  display:flex;
+  justify-content:center;
+}
+
+.image-box img{
+  width:100%;
+  max-width:900px;
+  border-radius:16px;
+  border:1px solid rgba(255,255,255,0.08);
+  background:var(--glass);
+  box-shadow:0 25px 50px rgba(0,0,0,0.5);
+}
+
+.divider{
+  height:2px;
+  width:100%;
+  background:var(--grad);
+  opacity:.6;
+}
+
+.card{
+  background:var(--panel);
+  padding:28px 30px;
+  border-radius:18px;
+  border:1px solid rgba(255,255,255,0.06);
+  box-shadow:0 12px 30px rgba(0,0,0,0.35);
+}
+
+.card-title{
+  margin:0 0 14px;
+  font-size:1.3rem;
+  text-transform:uppercase;
+  letter-spacing:.08em;
+  background:var(--grad);
+  -webkit-background-clip:text;
+  background-clip:text;
+  color:transparent;
+}
+
+.intro{
+  margin:0 0 12px;
+  color:var(--text-soft);
+}
+
+.card p{
+  margin:10px 0;
+  line-height:1.7;
+}
+
+.highlight{
+  color:var(--accent);
+  font-weight:700;
+}
+
+.link{
+  color:var(--accent2);
+  text-decoration:none;
+}
+.link:hover{
+  text-decoration:underline;
+}
+
+.config{
+  margin-top:18px;
+  border:1px solid rgba(255,255,255,0.08);
+  border-radius:12px;
+  overflow:hidden;
+  background:rgba(255,255,255,0.03);
+}
+
+.config summary{
+  padding:10px 14px;
+  cursor:pointer;
+  font-size:.85rem;
+  font-weight:600;
+  letter-spacing:.08em;
+  text-transform:uppercase;
+  background:rgba(255,255,255,0.05);
+  color:var(--accent);
+}
+
+.config pre{
+  margin:0;
+  padding:16px;
+  font-family:ui-monospace,Consolas,monospace;
+  font-size:.85rem;
+  overflow-x:auto;
+  background:rgba(0,0,0,0.35);
+  color:var(--text);
+}
+
+.grid{
+  display:flex;
+  gap:18px;
+  flex-wrap:wrap;
+  margin-top:16px;
+}
+
+.tile{
+  flex:1 1 180px;
+  padding:18px;
+  border-radius:14px;
+  background:rgba(255,255,255,0.05);
+  border:1px solid rgba(255,255,255,0.06);
+  text-align:center;
+}
+
+.tile-main{
+  display:block;
+  font-weight:700;
+  letter-spacing:.08em;
+  text-transform:uppercase;
+  color:var(--accent);
+  margin-bottom:6px;
+}
+
+.tile-sub{
+  font-size:.9rem;
+  color:var(--text-soft);
+}
+
+@media(max-width:600px){
+  .container{
+    padding:32px 24px;
+  }
+  .card{
+    padding:22px;
+  }
+}
+
+</style>

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,26 @@
+{
+  "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": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "vocab_size": 131075
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+
+base_model: Vortex5/Astral-Noctra-12B
+models:
+  - model: Vortex5/Starlit-Shadow-12B
+  - model: DreadPoor/Famino-12B-Model_Stock
+  - model: Vortex5/Crimson-Twilight-12B
+  - model: Vortex5/Astral-Noctra-12B
+merge_method: model_stock
+chat_template: auto
+parameters:
+  normalize: true
+dtype: float32
+out_dtype: bfloat16
+tokenizer:
+  source: Vortex5/Astral-Noctra-12B

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a882b31ad79b6e6cd21f724eb1b2167b778935ebbbc7e5b81b7f2a5c054f8284
+size 4865550776

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0207dc28ed50e92a207f24f15ea5e4c7b7d52b7ec93a332fa7f1028543946cc
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847200e0d7970375f290139ea561932040b6d292d7162a71e2e71f8c3c723e55
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6258c7865f0dac5e256e5d00296fd611daea5a36bdc5a3ef13a8a41e983fed7b
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68befc2f4e81bb37088b84dc34c43a4475ae62ed297428c3ea6b1f9be7e086bd
+size 4907529392

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