Upload folder using huggingface_hub

README.md

@@ -1,8 +1,8 @@
 ---
 base_model:
+- NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0
 - google/gemma-3-1b-it
 - google/gemma-3-1b-pt
-- NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0
 library_name: transformers
 tags:
 - mergekit
@@ -21,9 +21,9 @@ This model was merged using the Passthrough merge method.
 ### Models Merged
 
 The following models were included in the merge:
+* [NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0](https://huggingface.co/NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0)
 * [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it)
 * [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt)
-* [NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0](https://huggingface.co/NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0)
 
 ### Configuration
 
@@ -35,16 +35,16 @@ dtype: bfloat16
 merge_method: passthrough
 slices:
 - sources:
-  - layer_range: [2, 5]
+  - layer_range: [0, 2]
     model: google/gemma-3-1b-pt
 - sources:
-  - layer_range: [0, 26]
+  - layer_range: [3, 25]
     model: google/gemma-3-1b-it
 - sources:
-  - layer_range: [10, 16]
+  - layer_range: [10, 14]
     model: NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0
 - sources:
-  - layer_range: [23, 26]
+  - layer_range: [24, 26]
     model: google/gemma-3-1b-pt
 
 ```

config.json

@@ -7,10 +7,7 @@
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": [
-    1,
-    106
-  ],
+  "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
@@ -20,7 +17,7 @@
   "max_position_embeddings": 32768,
   "model_type": "gemma3_text",
   "num_attention_heads": 4,
-  "num_hidden_layers": 38,
+  "num_hidden_layers": 30,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
@@ -31,7 +28,9 @@
   "sliding_window": 512,
   "sliding_window_pattern": 6,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.1",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.19",
   "use_cache": true,
   "vocab_size": 262144
 }

mergekit_config.yml

@@ -3,14 +3,14 @@ dtype: bfloat16
 merge_method: passthrough
 slices:
 - sources:
-  - layer_range: [2, 5]
+  - layer_range: [0, 2]
     model: google/gemma-3-1b-pt
 - sources:
-  - layer_range: [0, 26]
+  - layer_range: [3, 25]
     model: google/gemma-3-1b-it
 - sources:
-  - layer_range: [10, 16]
+  - layer_range: [10, 14]
     model: NuclearAi/Nuke_X_Gemma3_1B_Reasoner_v1.0
 - sources:
-  - layer_range: [23, 26]
+  - layer_range: [24, 26]
     model: google/gemma-3-1b-pt

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adab3f4224d4c4b0b4e2c41863166817e92aad4933d1be0a689f94daa547ff15
-size 2644040072
+oid sha256:d3e37bd2e4eeaf13e20f9116fc3f7b9117287d134ae8378f7180b9893dd03ae3
+size 2214554160

special_tokens_map.json

@@ -9,7 +9,7 @@
   },
   "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<eos>",
+    "content": "<end_of_turn>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -51328,15 +51328,16 @@
   "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
-  "eos_token": "<eos>",
+  "eos_token": "<end_of_turn>",
   "extra_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": "<pad>",
+  "padding_side": "right",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,