Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+FLOR-6.3B-xat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

FLOR-6.3B-xat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8bc40d0360910c8de9546f0daf0484c3462b78af539b629ac68aa496f004db
+size 6863057344

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "projecte-aina/FLOR-6.3B",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_layer": 30,
+  "pretraining_tp": 1,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 12494528512
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.11.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.11.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.11.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.23.input_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.23.input_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00003.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00003.bin",
+    "transformer.h.23.self_attention.dense.bias": "model-00002-of-00003.bin",
+    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00003.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00003.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00003.bin",
+    "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.bin",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.dense.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.bin",
+    "transformer.ln_f.bias": "model-00003-of-00003.bin",
+    "transformer.ln_f.weight": "model-00003-of-00003.bin",
+    "transformer.word_embeddings.weight": "model-00001-of-00003.bin",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.bin",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}