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

README.md

@@ -0,0 +1,73 @@
+---
+base_model:
+- google/gemma-3-1b-pt
+- huihui-ai/gemma-3-1b-it-abliterated
+- prithivMLmods/gemma-3-1b-it-abliterated
+- lunahr/gemma-3-1b-it-abliterated
+- google/gemma-3-1b-pt
+tags:
+- merge
+- mergekit
+- lazymergekit
+- google/gemma-3-1b-pt
+- huihui-ai/gemma-3-1b-it-abliterated
+- prithivMLmods/gemma-3-1b-it-abliterated
+- lunahr/gemma-3-1b-it-abliterated
+---
+
+# gemma-3-1b-big
+
+gemma-3-1b-big is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt)
+* [huihui-ai/gemma-3-1b-it-abliterated](https://huggingface.co/huihui-ai/gemma-3-1b-it-abliterated)
+* [prithivMLmods/gemma-3-1b-it-abliterated](https://huggingface.co/prithivMLmods/gemma-3-1b-it-abliterated)
+* [lunahr/gemma-3-1b-it-abliterated](https://huggingface.co/lunahr/gemma-3-1b-it-abliterated)
+* [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt)
+
+## 🧩 Configuration
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 5]
+    model: google/gemma-3-1b-pt
+- sources:
+  - layer_range: [5, 10]
+    model: huihui-ai/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [10, 15]
+    model: prithivMLmods/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [15, 20]
+    model: lunahr/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [20, 25]
+    model: google/gemma-3-1b-pt
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Io2007/gemma-3-1b-big"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

added_tokens.json

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

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "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": 25,
+  "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": "4.50.3",
+  "use_cache": true,
+  "vocab_size": 262144
+}

mergekit_config.yml

@@ -0,0 +1,19 @@
+
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 5]
+    model: google/gemma-3-1b-pt
+- sources:
+  - layer_range: [5, 10]
+    model: huihui-ai/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [10, 15]
+    model: prithivMLmods/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [15, 20]
+    model: lunahr/gemma-3-1b-it-abliterated
+- sources:
+  - layer_range: [20, 25]
+    model: google/gemma-3-1b-pt

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c7b710fba668105304f0a7faf1148bce16cdbf8eeab6b5d0253ab127147527
+size 1946125472

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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": "<eos>",
+  "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