Add files using upload-large-folder tool

.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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention",
+    "full_attention", "full_attention", "full_attention", "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 6144,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_moe_config.yml

@@ -0,0 +1,80 @@
+base_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated
+architecture: Qwen3 MoE
+gate_mode: hidden
+dtype: bfloat16
+
+# NOTE: We are forcing 32 experts to satisfy llama.cpp power-of-two requirements.
+experts:
+  # --- ANCHORS (1-4) ---
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated
+    positive_prompts: ["consistent reasoning", "logical identity"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated
+    positive_prompts: ["identity coherence", "stable persona"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated
+    positive_prompts: ["scholarly abstraction", "formal tone"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated
+    positive_prompts: ["identity anchor", "core system"]
+
+  # --- SCHOLARS (5-8) ---
+  - source_model: D:\AI\Models\Cold-Storage\Kimina-Prover-Distill-1.7B
+    positive_prompts: ["formal proof", "mathematical rigor"]
+  - source_model: D:\AI\Models\Cold-Storage\Kimina-Prover-Distill-1.7B
+    positive_prompts: ["symbolic logic", "theorem construction"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-SFT-math
+    positive_prompts: ["numerical reasoning", "precise calculation"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-SFT-math
+    positive_prompts: ["geometric intuition", "spatial measurement"]
+
+  # --- DARK POETS (9-16) ---
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-Nyx-V3
+    positive_prompts: ["visceral imagery", "blood and shadow"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-Nyx-V3
+    positive_prompts: ["decay and ruin", "bleak atmosphere"]
+  - source_model: D:\AI\Models\Cold-Storage\PsyLLM-1.7B
+    positive_prompts: ["inner turmoil", "emotional trauma"]
+  - source_model: D:\AI\Models\Cold-Storage\PsyLLM-1.7B
+    positive_prompts: ["fractured identity", "psychological depth"]
+  - source_model: D:\AI\Models\Cold-Storage\Josiefied-Qwen3-1.7B
+    positive_prompts: ["explicit violence", "brutal realism"]
+  - source_model: D:\AI\Models\Cold-Storage\Josiefied-Qwen3-1.7B
+    positive_prompts: ["dark fantasy brutality", "grim tactility"]
+  - source_model: D:\AI\Models\Cold-Storage\DAN-Qwen3-1.7B
+    positive_prompts: ["profanity", "hostile dialogue"]
+  - source_model: D:\AI\Models\Cold-Storage\DAN-Qwen3-1.7B
+    positive_prompts: ["unrestricted speech", "raw expression"]
+
+  # --- BARDS (17-24) ---
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-Catgirl-v2.5
+    positive_prompts: ["vivid description", "social atmosphere"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-Catgirl-v2.5
+    positive_prompts: ["expressive dialogue", "playful banter"]
+  - source_model: D:\AI\Models\Cold-Storage\Hito-1.7b
+    positive_prompts: ["regional accents", "colloquial speech"]
+  - source_model: D:\AI\Models\Cold-Storage\Hito-1.7b
+    positive_prompts: ["travelers and merchants", "grounded interactions"]
+  - source_model: D:\AI\Models\Cold-Storage\Jinx-Qwen3-1.7B
+    positive_prompts: ["quest generation", "branching narrative"]
+  - source_model: D:\AI\Models\Cold-Storage\Jinx-Qwen3-1.7B
+    positive_prompts: ["world reactivity", "cause and effect"]
+  - source_model: D:\AI\Models\Cold-Storage\Lucy-128k
+    positive_prompts: ["ancient lore", "mythic history"]
+  - source_model: D:\AI\Models\Cold-Storage\Lucy-128k
+    positive_prompts: ["historical continuity", "layered worldbuilding"]
+
+  # --- DIVERGENCE (25-32) ---
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-FreeSteer-v4
+    positive_prompts: ["unpredictability", "narrative surprise"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-FreeSteer-v4
+    positive_prompts: ["tonal shifts", "spontaneous behavior"]
+  - source_model: D:\AI\Models\Cold-Storage\Polaris-1.7B
+    positive_prompts: ["philosophical inquiry", "abstract meaning"]
+  - source_model: D:\AI\Models\Cold-Storage\Polaris-1.7B
+    positive_prompts: ["existential themes", "metaphysical debate"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-ShiningValiant3
+    positive_prompts: ["heroic prose", "high fantasy drama"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-ShiningValiant3
+    positive_prompts: ["epic scale", "noble ideals"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated-v2
+    positive_prompts: ["instruction precision", "clarity of intent"]
+  - source_model: D:\AI\Models\Cold-Storage\Qwen3-1.7B-abliterated-v2
+    positive_prompts: ["execution reliability", "fallback competence"]

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb14a2de66f6bb41f116ba4bb7b55f329c9e22ba428e12e3e22ee789a97eff7d
+size 4976052696

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299b4960d5bd2f59344655f4476c029719b92b0fe589bf211787ec7e02a80191
+size 4982876640

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebb4fe73c9df8f4a5b23b77510c5e046ba0029a29a0a72f5f46c4e0fe10341b
+size 4982876640

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78519ef7dde26c2d6a48dfda48738fba9d3dc51ae1214f13b67b1d0e816bf98f
+size 4982876640

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c86e350a4f08d110c2e00c67cd92a97cceab054335867af85f6ea5b5bb1fe4
+size 4982876640

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdca35e693ba4bff741d3403b6c6d9feb70b6737b7da7ba235a17f44abf2a60
+size 4999659368

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5227c0444bca32045c053bef54ed23ae05828cf5516a26b0887e8a3e902ab21f
+size 4991269792

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1839f06c8de3705c3096d70c2166094ce7cb9f7cca992b98ff70e6ba61f6c94
+size 4982876872

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd5014d87699cffb39e0de33f2a43ee4dd4e56e8c5c3b8c5d47277c04b6f8b2
+size 4982876872

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9f3a81418d468a95564f60df67608e94bb41599cb6ed451814c7a5fa178f25
+size 4982876880

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678731b3f56c5ecea66fc2bcdfd60c302e446ac887e93f995f7faac1c62bcb0b
+size 4982876880

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799470b4818d2a6ef74b1f364c26d1e487d91ae41da4bb7db543184eacaa076f
+size 4982876880

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8646e3a46e99c3649ce65a5d55d402f49954ba94677c53eaf12acab811d0d8b
+size 4982876880

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084fb0703f6abeb85142c58c454bdd72e9aa18d75086ba44597295af6d5a8e1f
+size 4181239368

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de053c72a4ae289224ac988558897303006ceea1db22f30b97d0d856969ea6b9
+size 11422818

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}