Upload folder using huggingface_hub

README.md

@@ -1,37 +1,43 @@
 ---
 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
+- prithivMLmods/gemma-3-1b-it-abliterated
 - google/gemma-3-1b-pt
+- huihui-ai/gemma-3-1b-it-abliterated
+library_name: transformers
 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
+- merge
+
 ---
+# merge
 
-# gemma-3-1b-big
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-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)
+## Merge Details
+### Merge Method
+
+This model was merged using the Passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
 * [lunahr/gemma-3-1b-it-abliterated](https://huggingface.co/lunahr/gemma-3-1b-it-abliterated)
+* [prithivMLmods/gemma-3-1b-it-abliterated](https://huggingface.co/prithivMLmods/gemma-3-1b-it-abliterated)
 * [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)
+
+### Configuration
 
-## 🧩 Configuration
+The following YAML configuration was used to produce this model:
 
 ```yaml
+
 dtype: bfloat16
 merge_method: passthrough
 slices:
 - sources:
-  - layer_range: [0, 5]
+  - layer_range: [0, 7]
     model: google/gemma-3-1b-pt
 - sources:
   - layer_range: [5, 10]
@@ -43,31 +49,7 @@ slices:
   - layer_range: [15, 20]
     model: lunahr/gemma-3-1b-it-abliterated
 - sources:
-  - layer_range: [20, 25]
+  - layer_range: [19, 26]
     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

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

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": 1,
   "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": 25,
+  "num_hidden_layers": 29,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,

mergekit_config.yml

@@ -3,7 +3,7 @@ dtype: bfloat16
 merge_method: passthrough
 slices:
 - sources:
-  - layer_range: [0, 5]
+  - layer_range: [0, 7]
     model: google/gemma-3-1b-pt
 - sources:
   - layer_range: [5, 10]
@@ -15,5 +15,5 @@ slices:
   - layer_range: [15, 20]
     model: lunahr/gemma-3-1b-it-abliterated
 - sources:
-  - layer_range: [20, 25]
+  - layer_range: [19, 26]
     model: google/gemma-3-1b-pt

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c7b710fba668105304f0a7faf1148bce16cdbf8eeab6b5d0253ab127147527
-size 1946125472
+oid sha256:7818ace264d1dceb7013007417abceaa79e8ad8cb10d28d24614de79337d19ee
+size 2160868424

special_tokens_map.json

@@ -1,27 +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": "<eos>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "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
+  }
+}