add sharded checkpoint

.gitattributes

@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00007-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00008-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00008.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,25 @@
+{
+ "_name_or_path": "stabilityai/stablelm-tuned-alpha-3b",
+ "architectures": [
+ "GPTNeoXForCausalLM"
+ ],
+ "bos_token_id": 0,
+ "eos_token_id": 0,
+ "hidden_act": "gelu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 16384,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 4096,
+ "model_type": "gpt_neox",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 16,
+ "rotary_emb_base": 10000,
+ "rotary_pct": 0.25,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.28.1",
+ "use_cache": true,
+ "use_parallel_residual": true,
+ "vocab_size": 50688
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 0,
+ "eos_token_id": 0,
+ "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c87bddcc015f5819cf9db4c912e1cf2bd5cf0f00d227ae913734818148cbf24
+size 1938121717

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e94cc0e0c0bba08958b874bbef9b6aa4458595db11abe7673b2dbf53d8b6f0
+size 1913104975

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4544b39416978769d22175456e47bb6c27998cdfc6157c63cb3357f3af56e6cb
+size 1929901005

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3812ec59639b1e89720a3ff5586da17c25dde580986152173d0a44fe2b1ef7
+size 1913105651

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dccf24a4ca29b168faef7c744df46224e0885465d7588e76a83663fdd3539ce
+size 1913104975

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f58b3c74cf9fac7f69940f12bb41a02c30e4a84f7d3552b41f1d3ba52296738
+size 1929901005

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f04d31ed86e9a74d7c9b005af344a0585ebc31a925e6821fb8fc0aa08a666a3
+size 1913105715

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b589393ddd570995a89de7f175cadf1b12973784334685a616c57b84c0fbe96
+size 1367460560

pytorch_model.bin.index.json

@@ -0,0 +1,251 @@
+{
+ "metadata": {
+ "total_size": 14582842432.0
+ },
+ "weight_map": {
+ "embed_out.weight": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.final_layer_norm.bias": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.final_layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+ "gpt_neox.layers.10.attention.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.11.attention.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.attention.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+ "gpt_neox.layers.14.attention.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00008.bin",
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+ "gpt_neox.layers.2.attention.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+ "gpt_neox.layers.4.attention.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.attention.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+ "gpt_neox.layers.7.attention.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+ "gpt_neox.layers.9.attention.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin"
+ }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+ "add_prefix_space": false,
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1000000000000000019884624838656,
+ "tokenizer_class": "GPTNeoXTokenizer",
+ "unk_token": "<|endoftext|>"
+}