Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+base_model:
+- rinna/bilingual-gpt-neox-4b
+- rinna/japanese-gpt-neox-3.6b
+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 [rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [rinna/bilingual-gpt-neox-4b](https://huggingface.co/rinna/bilingual-gpt-neox-4b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: rinna/bilingual-gpt-neox-4b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: rinna/japanese-gpt-neox-3.6b
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: float16
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "rinna/japanese-gpt-neox-3.6b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2816,
+  "initializer_range": 0.02,
+  "intermediate_size": 11264,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 22,
+  "num_hidden_layers": 36,
+  "partial_rotary_factor": 1.0,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: rinna/bilingual-gpt-neox-4b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: rinna/japanese-gpt-neox-3.6b
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f76cfece05b24346f946384b707cf5cd14b3c5295256d9fb35a71fbc9c254e
+size 981071792

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8b7f9ef2a97745cd804a4842774da78f5b9f8e10b2968a5573977e57e50915
+size 993901202

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d99147f8e832311553f88143188f2d3d977a5535a6ed3ad0ed1bdd2c2ddf1
+size 993901194

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46afadb060008af4c48661c53b903e23c325c0674e367307873d0217f1b18fe
+size 993901202

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469389579ae0cd80db18ccee6f2b1c941ab7a9a1afa590951c9967fd64c8b9e2
+size 993901202

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698df738e85b63e44e17c6ffef4f003b2fc219c4fe52fbe932d23f556348d2cb
+size 993901194

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d8ceee6392d90c78bf93255a68eaafcff3a66e6eb89d53aa23fddf87a1f073
+size 993901154

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e203f0107b7b7fc3af4bb1a2f557bc3bb3a897664a190d20b90dc9e52062504
+size 572069276

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 7516485192}, "weight_map": {"embed_out.weight": "model-00001-of-00008.safetensors", "gpt_neox.embed_in.weight": "model-00001-of-00008.safetensors", "gpt_neox.final_layer_norm.bias": "model-00001-of-00008.safetensors", "gpt_neox.final_layer_norm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.masked_bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.masked_bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00008.safetensors", "gpt_neox.layers.11.attention.query_key_value.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.input_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.masked_bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.masked_bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.masked_bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.masked_bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.masked_bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00008.safetensors", "gpt_neox.layers.16.attention.query_key_value.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.input_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.dense.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.dense.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.masked_bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.query_key_value.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.query_key_value.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.input_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.dense.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.dense.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.masked_bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.query_key_value.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.query_key_value.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.input_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.dense.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.dense.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.masked_bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.query_key_value.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.query_key_value.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.input_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.dense.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.dense.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.masked_bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.query_key_value.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.query_key_value.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.input_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.dense.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.dense.weight": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.masked_bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.query_key_value.bias": "model-00003-of-00008.safetensors", "gpt_neox.layers.20.attention.query_key_value.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.input_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.dense.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.dense.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.masked_bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.query_key_value.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.query_key_value.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.input_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.dense.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.dense.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.masked_bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.query_key_value.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.query_key_value.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.input_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.dense.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.dense.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.masked_bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.query_key_value.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.query_key_value.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.input_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.dense.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.dense.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.masked_bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.query_key_value.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.query_key_value.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.input_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.dense.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.dense.weight": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.masked_bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.query_key_value.bias": "model-00004-of-00008.safetensors", "gpt_neox.layers.25.attention.query_key_value.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.input_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.dense.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.dense.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.masked_bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.query_key_value.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.query_key_value.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.input_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.dense.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.dense.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.masked_bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.query_key_value.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.query_key_value.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.input_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.dense.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.dense.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.masked_bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.query_key_value.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.query_key_value.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.input_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.dense.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.dense.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.masked_bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.query_key_value.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.query_key_value.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.input_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.dense.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.dense.weight": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.masked_bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.query_key_value.bias": "model-00005-of-00008.safetensors", "gpt_neox.layers.3.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.input_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.dense.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.dense.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.masked_bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.input_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.dense.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.dense.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.masked_bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.input_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.dense.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.dense.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.masked_bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.input_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.dense.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.dense.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.masked_bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.input_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.dense.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.dense.weight": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.masked_bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "gpt_neox.layers.34.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.input_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.dense.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.dense.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.masked_bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.input_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.dense.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.dense.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.masked_bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.input_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.dense.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.dense.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.masked_bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.input_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.dense.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.dense.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.masked_bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.input_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.dense.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.dense.weight": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.masked_bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "gpt_neox.layers.7.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.input_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.input_layernorm.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.dense.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.dense.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.masked_bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.input_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.input_layernorm.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.dense.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.dense.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.masked_bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.input_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
+size 786216

tokenizer_config.json

@@ -0,0 +1,76 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}