Upload merged model NTIS/merged_ko_slerp_gemma3_1b_cpt_final_checkpoint_10000_v0_20250610

.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

README.md

@@ -0,0 +1,47 @@
+---
+base_model:
+- google/gemma-3-1b-it
+- NTIS/gemma3-1b-cpt-final-checkpoint-10000
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged_ko_slerp_gemma3_1b_cpt_final_checkpoint_10000_v0_20250610
+
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it)
+* [NTIS/gemma3-1b-cpt-final-checkpoint-10000](https://huggingface.co/NTIS/gemma3-1b-cpt-final-checkpoint-10000)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: NTIS/gemma3-1b-cpt-final-checkpoint-10000
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t: 0.5
+slices:
+- sources:
+  - layer_range:
+    - 0
+    - 18
+    model: NTIS/gemma3-1b-cpt-final-checkpoint-10000
+  - layer_range:
+    - 0
+    - 18
+    model: google/gemma-3-1b-it
+
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 262144
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+base_model: NTIS/gemma3-1b-cpt-final-checkpoint-10000
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t: 0.5
+slices:
+- sources:
+  - layer_range:
+    - 0
+    - 18
+    model: NTIS/gemma3-1b-cpt-final-checkpoint-10000
+  - layer_range:
+    - 0
+    - 18
+    model: google/gemma-3-1b-it

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c848fab9bdead7bb79776b6218856f15877a6b10a57a3b21388f993bfcba60
+size 2174305352

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