Upload folder using huggingface_hub

README.md

@@ -0,0 +1,88 @@
+---
+base_model:
+- gpt2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [gpt2](https://huggingface.co/gpt2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 16,
+  "n_positions": 1024,
+  "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": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

mergekit_config.yml

@@ -0,0 +1,58 @@
+slices:
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+  - sources:
+      - layer_range: [0, 1]
+        model: gpt2
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700f5e277458a7ec5e65cb72db92ace61d8ec2fa920f1c3aae917eb24ff649ab
+size 305600264

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 305582592}, "weight_map": {"h.15.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.14.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.13.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.12.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.15.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.14.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.13.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.12.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.15.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.14.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.13.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.12.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.15.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.14.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.13.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.12.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.15.ln_1.bias": "model-00001-of-00001.safetensors", "h.14.ln_1.bias": "model-00001-of-00001.safetensors", "h.13.ln_1.bias": "model-00001-of-00001.safetensors", "h.12.ln_1.bias": "model-00001-of-00001.safetensors", "h.11.ln_1.bias": "model-00001-of-00001.safetensors", "h.10.ln_1.bias": "model-00001-of-00001.safetensors", "h.9.ln_1.bias": "model-00001-of-00001.safetensors", "h.8.ln_1.bias": "model-00001-of-00001.safetensors", "h.7.ln_1.bias": "model-00001-of-00001.safetensors", "h.6.ln_1.bias": "model-00001-of-00001.safetensors", "h.5.ln_1.bias": "model-00001-of-00001.safetensors", "h.4.ln_1.bias": "model-00001-of-00001.safetensors", "h.3.ln_1.bias": "model-00001-of-00001.safetensors", "h.2.ln_1.bias": "model-00001-of-00001.safetensors", "h.1.ln_1.bias": "model-00001-of-00001.safetensors", "h.0.ln_1.bias": "model-00001-of-00001.safetensors", "h.15.ln_1.weight": "model-00001-of-00001.safetensors", "h.14.ln_1.weight": "model-00001-of-00001.safetensors", "h.13.ln_1.weight": "model-00001-of-00001.safetensors", "h.12.ln_1.weight": "model-00001-of-00001.safetensors", "h.11.ln_1.weight": "model-00001-of-00001.safetensors", "h.10.ln_1.weight": "model-00001-of-00001.safetensors", "h.9.ln_1.weight": "model-00001-of-00001.safetensors", "h.8.ln_1.weight": "model-00001-of-00001.safetensors", "h.7.ln_1.weight": "model-00001-of-00001.safetensors", "h.6.ln_1.weight": "model-00001-of-00001.safetensors", "h.5.ln_1.weight": "model-00001-of-00001.safetensors", "h.4.ln_1.weight": "model-00001-of-00001.safetensors", "h.3.ln_1.weight": "model-00001-of-00001.safetensors", "h.2.ln_1.weight": "model-00001-of-00001.safetensors", "h.1.ln_1.weight": "model-00001-of-00001.safetensors", "h.0.ln_1.weight": "model-00001-of-00001.safetensors", "h.15.ln_2.bias": "model-00001-of-00001.safetensors", "h.14.ln_2.bias": "model-00001-of-00001.safetensors", "h.13.ln_2.bias": "model-00001-of-00001.safetensors", "h.12.ln_2.bias": "model-00001-of-00001.safetensors", "h.11.ln_2.bias": "model-00001-of-00001.safetensors", "h.10.ln_2.bias": "model-00001-of-00001.safetensors", "h.9.ln_2.bias": "model-00001-of-00001.safetensors", "h.8.ln_2.bias": "model-00001-of-00001.safetensors", "h.7.ln_2.bias": "model-00001-of-00001.safetensors", "h.6.ln_2.bias": "model-00001-of-00001.safetensors", "h.5.ln_2.bias": "model-00001-of-00001.safetensors", "h.4.ln_2.bias": "model-00001-of-00001.safetensors", "h.3.ln_2.bias": "model-00001-of-00001.safetensors", "h.2.ln_2.bias": "model-00001-of-00001.safetensors", "h.1.ln_2.bias": "model-00001-of-00001.safetensors", "h.0.ln_2.bias": "model-00001-of-00001.safetensors", "h.15.ln_2.weight": "model-00001-of-00001.safetensors", "h.14.ln_2.weight": "model-00001-of-00001.safetensors", "h.13.ln_2.weight": "model-00001-of-00001.safetensors", "h.12.ln_2.weight": "model-00001-of-00001.safetensors", "h.11.ln_2.weight": "model-00001-of-00001.safetensors", "h.10.ln_2.weight": "model-00001-of-00001.safetensors", "h.9.ln_2.weight": "model-00001-of-00001.safetensors", "h.8.ln_2.weight": "model-00001-of-00001.safetensors", "h.7.ln_2.weight": "model-00001-of-00001.safetensors", "h.6.ln_2.weight": "model-00001-of-00001.safetensors", "h.5.ln_2.weight": "model-00001-of-00001.safetensors", "h.4.ln_2.weight": "model-00001-of-00001.safetensors", "h.3.ln_2.weight": "model-00001-of-00001.safetensors", "h.2.ln_2.weight": "model-00001-of-00001.safetensors", "h.1.ln_2.weight": "model-00001-of-00001.safetensors", "h.0.ln_2.weight": "model-00001-of-00001.safetensors", "h.15.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.14.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.13.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.12.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.15.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.14.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.13.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.12.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.15.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.14.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.13.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.12.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.15.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.14.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.13.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.12.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "ln_f.bias": "model-00001-of-00001.safetensors", "ln_f.weight": "model-00001-of-00001.safetensors", "wpe.weight": "model-00001-of-00001.safetensors", "wte.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}