Upload folder using huggingface_hub

README.md

@@ -0,0 +1,115 @@
+---
+base_model:
+- mllm-dev/gpt2_f_experiment_0
+- mllm-dev/gpt2_f_experiment_7
+- mllm-dev/gpt2_f_experiment_6
+- mllm-dev/gpt2_f_experiment_9
+- mllm-dev/gpt2_f_experiment_2
+- mllm-dev/gpt2_f_experiment_5
+- mllm-dev/gpt2_f_experiment_8
+- mllm-dev/gpt2_f_experiment_1
+- mllm-dev/gpt2_f_experiment_4
+- mllm-dev/gpt2_f_experiment_3
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# sean_test_merge_out
+
+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 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.
+
+### Models Merged
+
+The following models were included in the merge:
+* [mllm-dev/gpt2_f_experiment_7](https://huggingface.co/mllm-dev/gpt2_f_experiment_7)
+* [mllm-dev/gpt2_f_experiment_6](https://huggingface.co/mllm-dev/gpt2_f_experiment_6)
+* [mllm-dev/gpt2_f_experiment_9](https://huggingface.co/mllm-dev/gpt2_f_experiment_9)
+* [mllm-dev/gpt2_f_experiment_2](https://huggingface.co/mllm-dev/gpt2_f_experiment_2)
+* [mllm-dev/gpt2_f_experiment_5](https://huggingface.co/mllm-dev/gpt2_f_experiment_5)
+* [mllm-dev/gpt2_f_experiment_8](https://huggingface.co/mllm-dev/gpt2_f_experiment_8)
+* [mllm-dev/gpt2_f_experiment_1](https://huggingface.co/mllm-dev/gpt2_f_experiment_1)
+* [mllm-dev/gpt2_f_experiment_4](https://huggingface.co/mllm-dev/gpt2_f_experiment_4)
+* [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
+
+### 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
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_0
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_1
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_2
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_3
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_4
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_5
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_6
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_7
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_8
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_9
+    parameters:
+      weight: 0.1
+```

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "mllm-dev/gpt2_f_experiment_0",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "problem_type": "single_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

mergekit_config.yml

@@ -0,0 +1,69 @@
+base_model:
+  model:
+    path: mllm-dev/gpt2_f_experiment_0
+dtype: float16
+merge_method: dare_linear
+parameters:
+  normalize: 1.0
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_0
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_1
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_2
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_3
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_4
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_5
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_6
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_7
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_8
+    parameters:
+      weight: 0.1
+  - layer_range: [0, 12]
+    model:
+      model:
+        path: mllm-dev/gpt2_f_experiment_9
+    parameters:
+      weight: 0.1

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199bbba2ae7eac40e101bc7f4b828cbabdac8e8e3c135fb75d74e380fc957107
+size 248902264

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 248887296}, "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

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}