Upload folder using huggingface_hub

README.md

@@ -0,0 +1,28 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
+License: apache-2.0
+---
+
+# 405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.25
+
+405M_TIES-merge_pile_300B_into_german_200B_from_pile_replay25_density-0.25 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch](https://huggingface.co/btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch)
+
+## 🧩 Configuration
+
+\```yamlmodels:
+  - model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch
+    # no parameters necessary for base model
+  - model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
+    parameters:
+      density: 0.25
+      weight: 1.0
+merge_method: ties
+base_model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch
+parameters:
+  normalize: true
+dtype: float16\```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+models:
+  - model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch
+    # no parameters necessary for base model
+  - model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
+    parameters:
+      density: 0.25
+      weight: 1.0
+merge_method: ties
+base_model: btherien/JOB-3312838_410M_it-86245_tr-german-replay-25_scratch
+parameters:
+  normalize: true
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4de066f0e7a7f0c3652cc65e4d7e6083c913f0adb2abfb6e5cffea5e29f6ca
+size 810701896

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"embed_out.weight": "model-00001-of-00001.safetensors", "gpt_neox.final_layer_norm.weight": "model-00001-of-00001.safetensors", "gpt_neox.final_layer_norm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.embed_in.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}