Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+base_model:
+- openai-community/gpt2-xl
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: openai-community/gpt2-xl
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: openai-community/gpt2-xl
+    parameters:
+      density: 0.5
+      weight: 0.5
+
+merge_method: ties
+base_model: openai-community/gpt2-xl
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openai-community/gpt2-xl",
+  "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": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "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": "4.44.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+models:
+  - model: openai-community/gpt2-xl
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: openai-community/gpt2-xl
+    parameters:
+      density: 0.5
+      weight: 0.5
+
+merge_method: ties
+base_model: openai-community/gpt2-xl
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bc5a60c17717354b02f71dab0cc0f670f57638706d30ff538984cd709aaa68
+size 3115276168

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 3115222400}, "weight_map": {"h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.0.ln_1.bias": "model-00001-of-00001.safetensors", "h.0.ln_1.weight": "model-00001-of-00001.safetensors", "h.0.ln_2.bias": "model-00001-of-00001.safetensors", "h.0.ln_2.weight": "model-00001-of-00001.safetensors", "h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.1.ln_1.bias": "model-00001-of-00001.safetensors", "h.1.ln_1.weight": "model-00001-of-00001.safetensors", "h.1.ln_2.bias": "model-00001-of-00001.safetensors", "h.1.ln_2.weight": "model-00001-of-00001.safetensors", "h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.10.ln_1.bias": "model-00001-of-00001.safetensors", "h.10.ln_1.weight": "model-00001-of-00001.safetensors", "h.10.ln_2.bias": "model-00001-of-00001.safetensors", "h.10.ln_2.weight": "model-00001-of-00001.safetensors", "h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.11.ln_1.bias": "model-00001-of-00001.safetensors", "h.11.ln_1.weight": "model-00001-of-00001.safetensors", "h.11.ln_2.bias": "model-00001-of-00001.safetensors", "h.11.ln_2.weight": "model-00001-of-00001.safetensors", "h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.12.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.12.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.12.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.12.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.12.ln_1.bias": "model-00001-of-00001.safetensors", "h.12.ln_1.weight": "model-00001-of-00001.safetensors", "h.12.ln_2.bias": "model-00001-of-00001.safetensors", "h.12.ln_2.weight": "model-00001-of-00001.safetensors", "h.12.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.12.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.12.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.12.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.13.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.13.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.13.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.13.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.13.ln_1.bias": "model-00001-of-00001.safetensors", "h.13.ln_1.weight": "model-00001-of-00001.safetensors", "h.13.ln_2.bias": "model-00001-of-00001.safetensors", "h.13.ln_2.weight": "model-00001-of-00001.safetensors", "h.13.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.13.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.13.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.13.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.14.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.14.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.14.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.14.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.14.ln_1.bias": "model-00001-of-00001.safetensors", "h.14.ln_1.weight": "model-00001-of-00001.safetensors", "h.14.ln_2.bias": "model-00001-of-00001.safetensors", "h.14.ln_2.weight": "model-00001-of-00001.safetensors", "h.14.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.14.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.14.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.14.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.15.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.15.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.15.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.15.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.15.ln_1.bias": "model-00001-of-00001.safetensors", "h.15.ln_1.weight": "model-00001-of-00001.safetensors", "h.15.ln_2.bias": "model-00001-of-00001.safetensors", "h.15.ln_2.weight": "model-00001-of-00001.safetensors", "h.15.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.15.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.15.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.15.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.16.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.16.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.16.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.16.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.16.ln_1.bias": "model-00001-of-00001.safetensors", "h.16.ln_1.weight": "model-00001-of-00001.safetensors", "h.16.ln_2.bias": "model-00001-of-00001.safetensors", "h.16.ln_2.weight": "model-00001-of-00001.safetensors", "h.16.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.16.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.16.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.16.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.17.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.17.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.17.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.17.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.17.ln_1.bias": "model-00001-of-00001.safetensors", "h.17.ln_1.weight": "model-00001-of-00001.safetensors", "h.17.ln_2.bias": "model-00001-of-00001.safetensors", "h.17.ln_2.weight": "model-00001-of-00001.safetensors", "h.17.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.17.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.17.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.17.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.18.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.18.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.18.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.18.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.18.ln_1.bias": "model-00001-of-00001.safetensors", "h.18.ln_1.weight": "model-00001-of-00001.safetensors", "h.18.ln_2.bias": "model-00001-of-00001.safetensors", "h.18.ln_2.weight": "model-00001-of-00001.safetensors", "h.18.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.18.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.18.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.18.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.19.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.19.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.19.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.19.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.19.ln_1.bias": "model-00001-of-00001.safetensors", "h.19.ln_1.weight": "model-00001-of-00001.safetensors", "h.19.ln_2.bias": "model-00001-of-00001.safetensors", "h.19.ln_2.weight": "model-00001-of-00001.safetensors", "h.19.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.19.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.19.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.19.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.2.ln_1.bias": "model-00001-of-00001.safetensors", "h.2.ln_1.weight": "model-00001-of-00001.safetensors", "h.2.ln_2.bias": "model-00001-of-00001.safetensors", "h.2.ln_2.weight": "model-00001-of-00001.safetensors", "h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.20.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.20.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.20.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.20.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.20.ln_1.bias": "model-00001-of-00001.safetensors", "h.20.ln_1.weight": "model-00001-of-00001.safetensors", "h.20.ln_2.bias": "model-00001-of-00001.safetensors", "h.20.ln_2.weight": "model-00001-of-00001.safetensors", "h.20.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.20.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.20.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.20.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.21.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.21.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.21.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.21.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.21.ln_1.bias": "model-00001-of-00001.safetensors", "h.21.ln_1.weight": "model-00001-of-00001.safetensors", "h.21.ln_2.bias": "model-00001-of-00001.safetensors", "h.21.ln_2.weight": "model-00001-of-00001.safetensors", "h.21.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.21.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.21.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.21.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.22.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.22.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.22.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.22.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.22.ln_1.bias": "model-00001-of-00001.safetensors", "h.22.ln_1.weight": "model-00001-of-00001.safetensors", "h.22.ln_2.bias": "model-00001-of-00001.safetensors", "h.22.ln_2.weight": "model-00001-of-00001.safetensors", "h.22.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.22.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.22.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.22.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.23.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.23.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.23.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.23.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.23.ln_1.bias": "model-00001-of-00001.safetensors", "h.23.ln_1.weight": "model-00001-of-00001.safetensors", "h.23.ln_2.bias": "model-00001-of-00001.safetensors", "h.23.ln_2.weight": "model-00001-of-00001.safetensors", "h.23.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.23.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.23.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.23.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.24.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.24.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.24.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.24.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.24.ln_1.bias": "model-00001-of-00001.safetensors", "h.24.ln_1.weight": "model-00001-of-00001.safetensors", "h.24.ln_2.bias": "model-00001-of-00001.safetensors", "h.24.ln_2.weight": "model-00001-of-00001.safetensors", "h.24.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.24.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.24.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.24.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.25.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.25.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.25.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.25.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.25.ln_1.bias": "model-00001-of-00001.safetensors", "h.25.ln_1.weight": "model-00001-of-00001.safetensors", "h.25.ln_2.bias": "model-00001-of-00001.safetensors", "h.25.ln_2.weight": "model-00001-of-00001.safetensors", "h.25.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.25.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.25.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.25.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.26.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.26.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.26.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.26.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.26.ln_1.bias": "model-00001-of-00001.safetensors", "h.26.ln_1.weight": "model-00001-of-00001.safetensors", "h.26.ln_2.bias": "model-00001-of-00001.safetensors", "h.26.ln_2.weight": "model-00001-of-00001.safetensors", "h.26.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.26.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.26.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.26.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.27.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.27.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.27.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.27.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.27.ln_1.bias": "model-00001-of-00001.safetensors", "h.27.ln_1.weight": "model-00001-of-00001.safetensors", "h.27.ln_2.bias": "model-00001-of-00001.safetensors", "h.27.ln_2.weight": "model-00001-of-00001.safetensors", "h.27.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.27.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.27.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.27.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.28.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.28.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.28.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.28.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.28.ln_1.bias": "model-00001-of-00001.safetensors", "h.28.ln_1.weight": "model-00001-of-00001.safetensors", "h.28.ln_2.bias": "model-00001-of-00001.safetensors", "h.28.ln_2.weight": "model-00001-of-00001.safetensors", "h.28.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.28.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.28.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.28.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.29.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.29.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.29.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.29.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.29.ln_1.bias": "model-00001-of-00001.safetensors", "h.29.ln_1.weight": "model-00001-of-00001.safetensors", "h.29.ln_2.bias": "model-00001-of-00001.safetensors", "h.29.ln_2.weight": "model-00001-of-00001.safetensors", "h.29.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.29.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.29.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.29.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.3.ln_1.bias": "model-00001-of-00001.safetensors", "h.3.ln_1.weight": "model-00001-of-00001.safetensors", "h.3.ln_2.bias": "model-00001-of-00001.safetensors", "h.3.ln_2.weight": "model-00001-of-00001.safetensors", "h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.30.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.30.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.30.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.30.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.30.ln_1.bias": "model-00001-of-00001.safetensors", "h.30.ln_1.weight": "model-00001-of-00001.safetensors", "h.30.ln_2.bias": "model-00001-of-00001.safetensors", "h.30.ln_2.weight": "model-00001-of-00001.safetensors", "h.30.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.30.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.30.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.30.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.31.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.31.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.31.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.31.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.31.ln_1.bias": "model-00001-of-00001.safetensors", "h.31.ln_1.weight": "model-00001-of-00001.safetensors", "h.31.ln_2.bias": "model-00001-of-00001.safetensors", "h.31.ln_2.weight": "model-00001-of-00001.safetensors", "h.31.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.31.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.31.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.31.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.32.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.32.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.32.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.32.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.32.ln_1.bias": "model-00001-of-00001.safetensors", "h.32.ln_1.weight": "model-00001-of-00001.safetensors", "h.32.ln_2.bias": "model-00001-of-00001.safetensors", "h.32.ln_2.weight": "model-00001-of-00001.safetensors", "h.32.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.32.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.32.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.32.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.33.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.33.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.33.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.33.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.33.ln_1.bias": "model-00001-of-00001.safetensors", "h.33.ln_1.weight": "model-00001-of-00001.safetensors", "h.33.ln_2.bias": "model-00001-of-00001.safetensors", "h.33.ln_2.weight": "model-00001-of-00001.safetensors", "h.33.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.33.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.33.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.33.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.34.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.34.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.34.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.34.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.34.ln_1.bias": "model-00001-of-00001.safetensors", "h.34.ln_1.weight": "model-00001-of-00001.safetensors", "h.34.ln_2.bias": "model-00001-of-00001.safetensors", "h.34.ln_2.weight": "model-00001-of-00001.safetensors", "h.34.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.34.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.34.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.34.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.35.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.35.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.35.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.35.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.35.ln_1.bias": "model-00001-of-00001.safetensors", "h.35.ln_1.weight": "model-00001-of-00001.safetensors", "h.35.ln_2.bias": "model-00001-of-00001.safetensors", "h.35.ln_2.weight": "model-00001-of-00001.safetensors", "h.35.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.35.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.35.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.35.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.36.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.36.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.36.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.36.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.36.ln_1.bias": "model-00001-of-00001.safetensors", "h.36.ln_1.weight": "model-00001-of-00001.safetensors", "h.36.ln_2.bias": "model-00001-of-00001.safetensors", "h.36.ln_2.weight": "model-00001-of-00001.safetensors", "h.36.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.36.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.36.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.36.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.37.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.37.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.37.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.37.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.37.ln_1.bias": "model-00001-of-00001.safetensors", "h.37.ln_1.weight": "model-00001-of-00001.safetensors", "h.37.ln_2.bias": "model-00001-of-00001.safetensors", "h.37.ln_2.weight": "model-00001-of-00001.safetensors", "h.37.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.37.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.37.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.37.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.38.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.38.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.38.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.38.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.38.ln_1.bias": "model-00001-of-00001.safetensors", "h.38.ln_1.weight": "model-00001-of-00001.safetensors", "h.38.ln_2.bias": "model-00001-of-00001.safetensors", "h.38.ln_2.weight": "model-00001-of-00001.safetensors", "h.38.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.38.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.38.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.38.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.39.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.39.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.39.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.39.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.39.ln_1.bias": "model-00001-of-00001.safetensors", "h.39.ln_1.weight": "model-00001-of-00001.safetensors", "h.39.ln_2.bias": "model-00001-of-00001.safetensors", "h.39.ln_2.weight": "model-00001-of-00001.safetensors", "h.39.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.39.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.39.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.39.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.4.ln_1.bias": "model-00001-of-00001.safetensors", "h.4.ln_1.weight": "model-00001-of-00001.safetensors", "h.4.ln_2.bias": "model-00001-of-00001.safetensors", "h.4.ln_2.weight": "model-00001-of-00001.safetensors", "h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.40.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.40.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.40.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.40.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.40.ln_1.bias": "model-00001-of-00001.safetensors", "h.40.ln_1.weight": "model-00001-of-00001.safetensors", "h.40.ln_2.bias": "model-00001-of-00001.safetensors", "h.40.ln_2.weight": "model-00001-of-00001.safetensors", "h.40.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.40.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.40.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.40.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.41.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.41.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.41.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.41.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.41.ln_1.bias": "model-00001-of-00001.safetensors", "h.41.ln_1.weight": "model-00001-of-00001.safetensors", "h.41.ln_2.bias": "model-00001-of-00001.safetensors", "h.41.ln_2.weight": "model-00001-of-00001.safetensors", "h.41.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.41.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.41.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.41.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.42.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.42.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.42.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.42.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.42.ln_1.bias": "model-00001-of-00001.safetensors", "h.42.ln_1.weight": "model-00001-of-00001.safetensors", "h.42.ln_2.bias": "model-00001-of-00001.safetensors", "h.42.ln_2.weight": "model-00001-of-00001.safetensors", "h.42.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.42.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.42.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.42.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.43.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.43.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.43.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.43.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.43.ln_1.bias": "model-00001-of-00001.safetensors", "h.43.ln_1.weight": "model-00001-of-00001.safetensors", "h.43.ln_2.bias": "model-00001-of-00001.safetensors", "h.43.ln_2.weight": "model-00001-of-00001.safetensors", "h.43.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.43.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.43.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.43.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.44.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.44.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.44.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.44.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.44.ln_1.bias": "model-00001-of-00001.safetensors", "h.44.ln_1.weight": "model-00001-of-00001.safetensors", "h.44.ln_2.bias": "model-00001-of-00001.safetensors", "h.44.ln_2.weight": "model-00001-of-00001.safetensors", "h.44.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.44.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.44.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.44.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.45.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.45.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.45.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.45.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.45.ln_1.bias": "model-00001-of-00001.safetensors", "h.45.ln_1.weight": "model-00001-of-00001.safetensors", "h.45.ln_2.bias": "model-00001-of-00001.safetensors", "h.45.ln_2.weight": "model-00001-of-00001.safetensors", "h.45.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.45.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.45.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.45.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.46.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.46.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.46.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.46.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.46.ln_1.bias": "model-00001-of-00001.safetensors", "h.46.ln_1.weight": "model-00001-of-00001.safetensors", "h.46.ln_2.bias": "model-00001-of-00001.safetensors", "h.46.ln_2.weight": "model-00001-of-00001.safetensors", "h.46.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.46.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.46.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.46.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.47.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.47.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.47.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.47.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.47.ln_1.bias": "model-00001-of-00001.safetensors", "h.47.ln_1.weight": "model-00001-of-00001.safetensors", "h.47.ln_2.bias": "model-00001-of-00001.safetensors", "h.47.ln_2.weight": "model-00001-of-00001.safetensors", "h.47.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.47.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.47.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.47.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.5.ln_1.bias": "model-00001-of-00001.safetensors", "h.5.ln_1.weight": "model-00001-of-00001.safetensors", "h.5.ln_2.bias": "model-00001-of-00001.safetensors", "h.5.ln_2.weight": "model-00001-of-00001.safetensors", "h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.6.ln_1.bias": "model-00001-of-00001.safetensors", "h.6.ln_1.weight": "model-00001-of-00001.safetensors", "h.6.ln_2.bias": "model-00001-of-00001.safetensors", "h.6.ln_2.weight": "model-00001-of-00001.safetensors", "h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.7.ln_1.bias": "model-00001-of-00001.safetensors", "h.7.ln_1.weight": "model-00001-of-00001.safetensors", "h.7.ln_2.bias": "model-00001-of-00001.safetensors", "h.7.ln_2.weight": "model-00001-of-00001.safetensors", "h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.8.ln_1.bias": "model-00001-of-00001.safetensors", "h.8.ln_1.weight": "model-00001-of-00001.safetensors", "h.8.ln_2.bias": "model-00001-of-00001.safetensors", "h.8.ln_2.weight": "model-00001-of-00001.safetensors", "h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "h.9.ln_1.bias": "model-00001-of-00001.safetensors", "h.9.ln_1.weight": "model-00001-of-00001.safetensors", "h.9.ln_2.bias": "model-00001-of-00001.safetensors", "h.9.ln_2.weight": "model-00001-of-00001.safetensors", "h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "h.9.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": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}