Upload folder using huggingface_hub

README.md

@@ -1,10 +1,15 @@
 ---
 base_model:
+- mllm-dev/gpt2_f_experiment_9
+- mllm-dev/gpt2_f_experiment_8
+- mllm-dev/gpt2_f_experiment_6
+- mllm-dev/gpt2_f_experiment_2
+- mllm-dev/gpt2_f_experiment_7
+- mllm-dev/gpt2_f_experiment_4
 - mllm-dev/gpt2_f_experiment_0
 - mllm-dev/gpt2_f_experiment_1
-- mllm-dev/gpt2_f_experiment_4
+- mllm-dev/gpt2_f_experiment_5
 - mllm-dev/gpt2_f_experiment_3
-- mllm-dev/gpt2_f_experiment_2
 library_name: transformers
 tags:
 - mergekit
@@ -18,28 +23,29 @@ This is a merge of pre-trained language models created using [mergekit](https://
 ## Merge Details
 ### Merge Method
 
-This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [mllm-dev/gpt2_f_experiment_0](https://huggingface.co/mllm-dev/gpt2_f_experiment_0) as a base.
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
 
 ### Models Merged
 
 The following models were included in the merge:
-* [mllm-dev/gpt2_f_experiment_1](https://huggingface.co/mllm-dev/gpt2_f_experiment_1)
+* [mllm-dev/gpt2_f_experiment_9](https://huggingface.co/mllm-dev/gpt2_f_experiment_9)
+* [mllm-dev/gpt2_f_experiment_8](https://huggingface.co/mllm-dev/gpt2_f_experiment_8)
+* [mllm-dev/gpt2_f_experiment_6](https://huggingface.co/mllm-dev/gpt2_f_experiment_6)
+* [mllm-dev/gpt2_f_experiment_2](https://huggingface.co/mllm-dev/gpt2_f_experiment_2)
+* [mllm-dev/gpt2_f_experiment_7](https://huggingface.co/mllm-dev/gpt2_f_experiment_7)
 * [mllm-dev/gpt2_f_experiment_4](https://huggingface.co/mllm-dev/gpt2_f_experiment_4)
+* [mllm-dev/gpt2_f_experiment_0](https://huggingface.co/mllm-dev/gpt2_f_experiment_0)
+* [mllm-dev/gpt2_f_experiment_1](https://huggingface.co/mllm-dev/gpt2_f_experiment_1)
+* [mllm-dev/gpt2_f_experiment_5](https://huggingface.co/mllm-dev/gpt2_f_experiment_5)
 * [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
-* [mllm-dev/gpt2_f_experiment_2](https://huggingface.co/mllm-dev/gpt2_f_experiment_2)
 
 ### Configuration
 
 The following YAML configuration was used to produce this model:
 
 ```yaml
-base_model:
-  model:
-    path: mllm-dev/gpt2_f_experiment_0
 dtype: float16
-merge_method: dare_linear
-parameters:
-  normalize: 1.0
+merge_method: linear
 slices:
 - sources:
   - layer_range: [0, 12]
@@ -53,23 +59,53 @@ slices:
       model:
         path: mllm-dev/gpt2_f_experiment_1
     parameters:
-      weight: 1.3
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_2
     parameters:
-      weight: 1.5
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_3
     parameters:
-      weight: 0.2
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_4
     parameters:
-      weight: 0.2
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_5
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_6
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_7
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_8
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_9
+    parameters:
+      weight: 1.0
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mllm-dev/gpt2_f_experiment_0",
+  "_name_or_path": "mllm-dev/gpt2_f_experiment_9",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2ForSequenceClassification"

mergekit_config.yml

@@ -1,10 +1,5 @@
-base_model:
-  model:
-    path: mllm-dev/gpt2_f_experiment_0
 dtype: float16
-merge_method: dare_linear
-parameters:
-  normalize: 1.0
+merge_method: linear
 slices:
 - sources:
   - layer_range: [0, 12]
@@ -18,22 +13,52 @@ slices:
       model:
         path: mllm-dev/gpt2_f_experiment_1
     parameters:
-      weight: 1.3
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_2
     parameters:
-      weight: 1.5
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_3
     parameters:
-      weight: 0.2
+      weight: 1.0
   - layer_range: [0, 12]
     model:
       model:
         path: mllm-dev/gpt2_f_experiment_4
     parameters:
-      weight: 0.2
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_5
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_6
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_7
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_8
+    parameters:
+      weight: 1.0
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_9
+    parameters:
+      weight: 1.0

model-00001-of-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0985f810e843ad6e3cbeed498215211277ab07182b770c5eda9db14011f2c24a
+oid sha256:4bcf9cb71e14431636c4e43fda6cda1a4e795f63a07b9fef99febec161914707
 size 248902264

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"score.weight": "model-00001-of-00001.safetensors", "transformer.ln_f.bias": "model-00001-of-00001.safetensors", "transformer.ln_f.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.wpe.weight": "model-00001-of-00001.safetensors", "transformer.wte.weight": "model-00001-of-00001.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 0}, "weight_map": {"score.weight": "model-00001-of-00001.safetensors", "transformer.ln_f.bias": "model-00001-of-00001.safetensors", "transformer.ln_f.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.wpe.weight": "model-00001-of-00001.safetensors", "transformer.wte.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -2,28 +2,28 @@
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -9,7 +9,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],

tokenizer_config.json

@@ -4,7 +4,7 @@
     "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true