Upload folder using huggingface_hub

README.md

@@ -1,10 +1,10 @@
 ---
 base_model:
-- mllm-dev/gpt2_f_experiment_0_1000
-- mllm-dev/gpt2_f_experiment_3_1000
-- mllm-dev/gpt2_f_experiment_2_1000
 - mllm-dev/gpt2_f_experiment_1_1000
 - mllm-dev/gpt2_f_experiment_4_1000
+- mllm-dev/gpt2_f_experiment_3_1000
+- mllm-dev/gpt2_f_experiment_2_1000
+- mllm-dev/gpt2_f_experiment_0_1000
 library_name: transformers
 tags:
 - mergekit
@@ -18,15 +18,15 @@ This is a merge of pre-trained language models created using [mergekit](https://
 ## Merge Details
 ### Merge Method
 
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mllm-dev/gpt2_f_experiment_0_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_0_1000) as a base.
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mllm-dev/gpt2_f_experiment_1_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_1_1000) as a base.
 
 ### Models Merged
 
 The following models were included in the merge:
+* [mllm-dev/gpt2_f_experiment_4_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_4_1000)
 * [mllm-dev/gpt2_f_experiment_3_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_3_1000)
 * [mllm-dev/gpt2_f_experiment_2_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_2_1000)
-* [mllm-dev/gpt2_f_experiment_1_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_1_1000)
-* [mllm-dev/gpt2_f_experiment_4_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_4_1000)
+* [mllm-dev/gpt2_f_experiment_0_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_0_1000)
 
 ### Configuration
 
@@ -35,7 +35,7 @@ The following YAML configuration was used to produce this model:
 ```yaml
 base_model:
   model:
-    path: mllm-dev/gpt2_f_experiment_0_1000
+    path: mllm-dev/gpt2_f_experiment_1_1000
 dtype: float16
 merge_method: dare_ties
 parameters:
@@ -45,11 +45,11 @@ slices:
   - layer_range: [0, 12]
     model:
       model:
-        path: mllm-dev/gpt2_f_experiment_0_1000
+        path: mllm-dev/gpt2_f_experiment_1_1000
   - layer_range: [0, 12]
     model:
       model:
-        path: mllm-dev/gpt2_f_experiment_1_1000
+        path: mllm-dev/gpt2_f_experiment_0_1000
     parameters:
       density: 0.8
       weight: 0.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mllm-dev/gpt2_f_experiment_0_1000",
+  "_name_or_path": "mllm-dev/gpt2_f_experiment_1_1000",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2ForSequenceClassification"

mergekit_config.yml

@@ -1,6 +1,6 @@
 base_model:
   model:
-    path: mllm-dev/gpt2_f_experiment_0_1000
+    path: mllm-dev/gpt2_f_experiment_1_1000
 dtype: float16
 merge_method: dare_ties
 parameters:
@@ -10,11 +10,11 @@ slices:
   - layer_range: [0, 12]
     model:
       model:
-        path: mllm-dev/gpt2_f_experiment_0_1000
+        path: mllm-dev/gpt2_f_experiment_1_1000
   - layer_range: [0, 12]
     model:
       model:
-        path: mllm-dev/gpt2_f_experiment_1_1000
+        path: mllm-dev/gpt2_f_experiment_0_1000
     parameters:
       density: 0.8
       weight: 0.2

model-00001-of-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751d37329ac0cb3875dd22a5ef5cb1886c7238a90378cff2918ae05491ae9db0
+oid sha256:f0c4e976b3588d122d65ca3d4732e087356109eaa0e662609b3738547512252b
 size 248902264

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -13,8 +13,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }