DPO finetune of smartfalcon

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "../smartfalcon-1b-v1",
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.34.1"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3ca20ccfd6cb338ddd196f22195adf7bc2e2a59beb61584493c40f3f64ffb2
+size 373910528

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e9889dff63ff798636f881264fa3a7ad7a8424b54d446497b4e368e93c5770
+size 369311270

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc524196a181c3997212560f0cea25c8506dd732744b3d6f3c999ce974fc2bc5
+size 394489382

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a1f9e7412e8b1196af2c89a4b963a8076fc4f5d8fee0e3fac0d57becbebf92
+size 377703974

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10de3616becb8ba15987fbf49ccd3ee3711c8dee90b85cb9e2d9f56bf9d92b2
+size 369305886

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a360f239dbe5083bd2cc349b0d3576d77736f5df6b4259a037ad7458a78d50d
+size 369311334

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d124495b05965308abe2153720ecd38faadad29a755273c2c1d1e398de3ead
+size 369319398

pytorch_model.bin.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 2623250432
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}