Upload 17 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+Nemesia-Gemma3-12B-v2.0-F16.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Nemesia-Gemma3-12B-v2.0-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47475dfb6837d51e8fbc960b33769aeaea73f49be0ea99113a5cd71468eae41
+size 23540152096

README.md

@@ -1,3 +1,64 @@
 ---
-license: gemma
+base_model:
+- mlabonne/gemma-3-12b-it-abliterated
+- google/gemma-3-12b-it
+- qiuxi337/gemma-3-12b-it-grpo
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# temp
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the NuSLERP merge method using [mlabonne/gemma-3-12b-it-abliterated](https://huggingface.co/mlabonne/gemma-3-12b-it-abliterated) as a base.
+
+Well, it's been a while, hasn't it? It's only been a short 5 months since I posted the last Nemesia version, saying the famous last words 
+
+> I will try swapping out a model or two in the merge and trying again to upload as a v2.0.
+
+Then, exams and university stuff crushed me whole which wasn't great, and I didn't have any time or computational resources to get back to merging on a reasonable timeframe until now.
+
+Honestly, in the time since, Qwen2.5-7B really has not turned out to be all that interesting, Mistral Nemo stealing most of its thunder. So, I decided to update my Nemesia mergeset with a 
+new base: **Gemma3-12B**! In my experience, it has been alright, so I'm excited to tinker with it.
+
+In my testing, this thing is alright- I couldn't run any GGUFs of it since I don't even know what on earth has happened to my `.venv` in the 5 months past, I'm pretty sure my Transformers installation 
+is corrupted, and I'm re-cloning llama.cpp as I write this. I ran the FP16 and it seemed coherent enough, but I leave that to you to decide.
+
+Uses all of the special NuSLERP options because they're there, and is based on the abliterated version of Gemma3 instead of the base because I <3 mlabonne.
+
+### Models Merged
+
+The following models were included in the merge:
+* [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it)
+* [qiuxi337/gemma-3-12b-it-grpo](https://huggingface.co/qiuxi337/gemma-3-12b-it-grpo)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mlabonne/gemma-3-12b-it-abliterated
+    parameters:
+      weight: 1.0
+  - model: qiuxi337/gemma-3-12b-it-grpo
+    parameters:
+      weight: 0.5
+  - model: google/gemma-3-12b-it
+    parameters:
+      weight: 0.2
+merge_method: nuslerp
+base_model: mlabonne/gemma-3-12b-it-abliterated
+parameters:
+  normalize: true
+  int8_mask: true
+  nuslerp_flatten: false
+  nuslerp_row_wise: true
+dtype: float16
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+models:
+  - model: mlabonne/gemma-3-12b-it-abliterated
+    parameters:
+      weight: 1.0
+  - model: qiuxi337/gemma-3-12b-it-grpo
+    parameters:
+      weight: 0.5
+  - model: google/gemma-3-12b-it
+    parameters:
+      weight: 0.2
+merge_method: nuslerp
+base_model: mlabonne/gemma-3-12b-it-abliterated
+parameters:
+  normalize: true
+  int8_mask: true
+  nuslerp_flatten: false
+  nuslerp_row_wise: true
+dtype: float16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4e87bfc31218de4b01d23a8095552e2169f3e719ead934baec60949732d171
+size 4939493352

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b1c2f0c53647c22cdc719a7ef4a94a2d70d3333f451b5190f29cff55814567
+size 4931296512

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3778ec3c69fa20cf3a3bb0a7fc7074b613ce945ebcf4dc31742ba3d0fbb1bcd3
+size 4931296512

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00aa65941098a39998dace46d3bdbd70d577cee56e50efcb34cbe113207a622
+size 4931296512

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976d86a5b281df8a9a8ced0ffb935540ada0d438bab2c4e839b3e54704c53465
+size 4641409128

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074