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

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 81,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,389 @@
+# Six splits plus "end game
+# "D" starts at plus .1 VS D/O proj.
+# 40 plus.
+
+# Qwen 30B-a3B
+#
+# 	First block 		[5] 	47,48,49,50 
+# 	Second block 	[5] 	51,52,53,54 
+# 	Third block 		[12]	55,56,57,58,59,60,61,62,63,64,65,66
+# 	Fourth: 			[4] 	67,68,69,70
+# 	Fifth: 			[4] 	71,72,73,74
+# 	Sixth: 			[7] 	75,76,77,78,79,80,81
+# 	Final: 			[5] 	82,83,84,85,86
+#
+# --prune-layers 47,48,49,50  ,58,63
+
+slices:
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [0,47]
+
+# conc layers
+# split 1
+
+# prune 47,48,49,50
+
+# split 2, SURGE D THEN D drop .46, continues @ D .15 (from .13)
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.05
+         - filter: down_proj
+           value: 0.05
+         - value: 0.15
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.06
+         - filter: down_proj
+           value: 0.06
+         - value: 0.16
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.07
+         - filter: down_proj
+           value: 0.07
+         - value: 0.17
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.08
+         - filter: down_proj
+           value: 0.08
+         - value: 0.41
+
+# split 3, SURGE D to .41, D drop .21 ... follows .17 previous
+# 55 , prune 58, 63
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.09
+         - filter: down_proj
+           value: 0.09
+         - value: 0.19
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.10
+         - filter: down_proj
+           value: 0.10
+         - value: 0.20
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.11
+         - filter: down_proj
+           value: 0.11
+         - value: .22
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.13
+         - filter: down_proj
+           value: 0.13
+         - value: .26
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.14
+         - filter: down_proj
+           value: 0.14
+         - value: .28
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.15
+         - filter: down_proj
+           value: 0.15
+         - value: .30
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.16
+         - filter: down_proj
+           value: 0.16
+         - value: .31
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.21
+         - filter: down_proj
+           value: 0.21
+         - value: .33
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.22
+         - filter: down_proj
+           value: 0.22
+         - value: .34
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.23
+         - filter: down_proj
+           value: 0.23
+         - value: .35
+
+# split 4 , NO SURGE D, "D" down drop of .24 ; reverts to .11 (the very first "D" setting )
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.24
+         - filter: down_proj
+           value: 0.24
+         - value: 0.11
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.241
+         - filter: down_proj
+           value: 0.241
+         - value: 0.12
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.242
+         - filter: down_proj
+           value: 0.243
+         - value: 0.13
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.244
+         - filter: down_proj
+           value: 0.244
+         - value: 0.61
+
+# split 5, D Surge to .61, drop to .15 (following .13)
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.245
+         - filter: down_proj
+           value: 0.245
+         - value: 0.15
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.246
+         - filter: down_proj
+           value: 0.246
+         - value: 0.16
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.247
+         - filter: down_proj
+           value: 0.247
+         - value: 0.17
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.248
+         - filter: down_proj
+           value: 0.248
+         - value: 0.41
+
+# split 6, D surge to .41 , then follows .17 
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.249
+         - filter: down_proj
+           value: 0.249
+         - value: 0.19
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.250
+         - filter: down_proj
+           value: 0.250
+         - value: 0.20
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.251
+         - filter: down_proj
+           value: 0.251
+         - value: .22
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.252
+         - filter: down_proj
+           value: 0.252
+         - value: .24
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.253
+         - filter: down_proj
+           value: 0.254
+         - value: .26
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.255
+         - filter: down_proj
+           value: 0.255
+         - value: .28
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.256
+         - filter: down_proj
+           value: 0.256
+         - value: .30
+
+# O PROJ, DPROJ to .3333 / 
+# end game
+
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.3333333333333
+         - filter: down_proj
+           value: 0.3333333333333
+         - value: 0.3333333333333
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.4444444444444
+         - filter: down_proj
+           value: 0.4444444444444
+         - value: 0.4444444444444
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.5555555555555
+         - filter: down_proj
+           value: 0.5555555555555
+         - value: 0.5555555555555
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.6666666666666
+         - filter: down_proj
+           value: 0.6666666666666
+         - value: 0.6666666666666
+ - sources:
+   - model: D:/Qwen3-30B-A3B
+     layer_range: [47,48]
+     parameters:
+       scale:
+         - filter: o_proj
+           value: 0.777777777777
+         - filter: down_proj
+           value: 0.777777777777
+         - value: 0.888888888888
+merge_method: passthrough
+dtype: float16

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}