update model weights

.gitattributes

@@ -56,3 +56,24 @@ pytorch_model-00004-of-00021.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00005-of-00021.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00009-of-00021.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00012-of-00021.bin filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00018-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00020-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00021-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00012-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00016-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00013-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00014-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00015-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00017-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00019-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -2,6 +2,7 @@
   "architectures": [
     "InternLM2ForCausalLM"
   ],
+  "attn_implementation": "eager",
   "auto_map": {
     "AutoConfig": "configuration_internlm2.InternLM2Config",
     "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
@@ -21,14 +22,11 @@
   "num_key_value_heads": 8,
   "pad_token_id": 2,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 3.0,
-    "type": "dynamic"
-  },
+  "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.33.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
   "use_cache": true,
   "vocab_size": 92544
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.37.1"
 }

pytorch_model-00001-of-00021.bin → model-00001-of-00021.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722819f7b217898ee32c8c65421006303081106b7af8048378774423de824f26
-size 1917348897
+oid sha256:71c97753e79aca0ec02fce767a8eb577a22a8d71f85f67ad1a0d27ad180de9b9
+size 1917346712

pytorch_model-00002-of-00021.bin → model-00002-of-00021.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4ee6af265497cbd169c7163f0e9ac97c56e389c7a89f825713894ff3120fee
-size 1937823489
+oid sha256:1d7d3e8a363a51541d73fc3aa4d09f5101ec2112ea1f606b3d299e60d786fa65
+size 1937819544

pytorch_model-00003-of-00021.bin → model-00003-of-00021.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0d11d9813cea7bba73cfbcc0e212fff344e7282adb370fdfb20adfda9f164a
-size 1963014163
+oid sha256:c42aeb776313b0457193e34cf67449635e16d58fd458a33ea7de8f9ca4a6c2f7
+size 1963010040

pytorch_model-00004-of-00021.bin → model-00004-of-00021.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa74f5be136e888c2a7c43032bd97dca226d8644ec06ec6cef986a3f5be375be
-size 1937823489
+oid sha256:f150d613778a94eecd9767d22481f885c5ea7cc6930447571419b636531fe458
+size 1937819544

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ae67ff1640d2240ee39e4ad8afd6434f65dfea8edcda3e5a65228b56681c40
+size 1963010056

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458d174c5f58e614eb9a4866e640658eb3fa3d693c82c121cf81305a4c7524d5
+size 1937819560

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26ee729dd0f56ce9a7b9ee7cb76a0db088652d8f2e6bc804fd90ac33516124c
+size 1963010064

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a950b8704d16a20578a7c81dc8839277567287a588beb813e6d11a615b7709
+size 1937819560

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b698ce7143053027afcd9ffb111a02ea11ffe63ec8ee7e9173632ada39352a13
+size 1963010064

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad08486a3e53b09f31d59d583e5101742bebcfe9f16a6197cd904fb915e62ad
+size 1937819560

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14726e3d81b00c9529cd10ac5715fca78d33d73dda86dae0486907d6b2d43586
+size 1963010064

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f9422d667749b9c111eca0e0267c38595fb5187502cc6ed59ed3759cd578ff
+size 1937819560

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c762ae1adefb90c623ec485eef484c2c530d5de4b9b450e58b5c01fac5f8141
+size 1963010064

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a58657add48c89e0c685a4c33d202bd390d3f891cf1b0c540845ac743e8783
+size 1937819560

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c843c57fb031e3307915b59f659d5f3ca7065167a5aee6a9898ecbd982a8b169
+size 1963010064

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9b9280c441514ad0ef3f4c0f4771f220b1453728a142bc03d6130705d554f2
+size 1937819560

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d01c0d63e0ba5178c138258d2492c2767d5af52ee66657e8efcb9fef221e37
+size 1963010064

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b4ffe7d27ebda067452ad0ece09b134132097cfcea3c147860086705e2737b
+size 1937819560

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4970740b6cf6d32721167a8ceb7503ee162c0e9ebbcaabf60339cb07799bc95
+size 1963010064

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11549f6e010488fd2c9f3e7e4f83b4a27d52b30b878de2287753c5d2c199ab1f
+size 1560344232

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc8dffc3abaed006d85b1ac1f3d9eb1f5d32c3cfb105525111af0c559dd9e78
+size 1137180800

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 39722299392
+  },
+  "weight_map": {
+    "model.layers.0.attention.wo.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.attention.wqkv.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.feed_forward.w1.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.feed_forward.w2.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00021.safetensors",
+    "model.layers.1.attention.wo.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.attention.wqkv.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.feed_forward.w2.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.10.attention.wo.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.attention.wqkv.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.feed_forward.w1.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.11.attention.wo.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.attention.wqkv.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.feed_forward.w2.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.attention.wo.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.attention.wqkv.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.feed_forward.w2.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.attention.wo.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.attention.wqkv.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
+    "model.layers.13.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.attention.wo.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.attention.wqkv.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.feed_forward.w1.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.attention.wo.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.attention.wqkv.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.feed_forward.w1.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.16.attention.wo.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.attention.wqkv.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.feed_forward.w2.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.attention.wo.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.attention.wqkv.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.feed_forward.w2.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00008-of-00021.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.attention.wo.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.attention.wqkv.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
+    "model.layers.18.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.attention.wo.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.attention.wqkv.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.feed_forward.w1.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.2.attention.wo.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.attention.wqkv.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.feed_forward.w2.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.20.attention.wo.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.attention.wqkv.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.feed_forward.w1.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.21.attention.wo.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.attention.wqkv.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.feed_forward.w2.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00010-of-00021.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.attention.wo.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.attention.wqkv.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.feed_forward.w2.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00010-of-00021.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.23.attention.wo.weight": "model-00010-of-00021.safetensors",
+    "model.layers.23.attention.wqkv.weight": "model-00010-of-00021.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.23.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
+    "model.layers.23.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.attention.wo.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.attention.wqkv.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.attention_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.feed_forward.w1.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
+    "model.layers.24.ffn_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.attention.wo.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.attention.wqkv.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.attention_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.feed_forward.w1.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
+    "model.layers.25.ffn_norm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.26.attention.wo.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.attention.wqkv.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.attention_norm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.feed_forward.w2.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.feed_forward.w3.weight": "model-00012-of-00021.safetensors",
+    "model.layers.26.ffn_norm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.attention.wo.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.attention.wqkv.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.attention_norm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.feed_forward.w2.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.feed_forward.w3.weight": "model-00012-of-00021.safetensors",
+    "model.layers.27.ffn_norm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.28.attention.wo.weight": "model-00012-of-00021.safetensors",
+    "model.layers.28.attention.wqkv.weight": "model-00012-of-00021.safetensors",
+    "model.layers.28.attention_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.28.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
+    "model.layers.28.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
+    "model.layers.28.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
+    "model.layers.28.ffn_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.attention.wo.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.attention.wqkv.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.attention_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.feed_forward.w1.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
+    "model.layers.29.ffn_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.3.attention.wo.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.attention.wqkv.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.30.attention.wo.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.attention.wqkv.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.attention_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.feed_forward.w1.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
+    "model.layers.30.ffn_norm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.31.attention.wo.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.attention.wqkv.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.attention_norm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.feed_forward.w2.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.feed_forward.w3.weight": "model-00014-of-00021.safetensors",
+    "model.layers.31.ffn_norm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.attention.wo.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.attention.wqkv.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.attention_norm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.feed_forward.w2.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.feed_forward.w3.weight": "model-00014-of-00021.safetensors",
+    "model.layers.32.ffn_norm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.33.attention.wo.weight": "model-00014-of-00021.safetensors",
+    "model.layers.33.attention.wqkv.weight": "model-00014-of-00021.safetensors",
+    "model.layers.33.attention_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.33.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
+    "model.layers.33.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
+    "model.layers.33.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
+    "model.layers.33.ffn_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.attention.wo.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.attention.wqkv.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.attention_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.feed_forward.w1.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
+    "model.layers.34.ffn_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.attention.wo.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.attention.wqkv.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.attention_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.feed_forward.w1.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
+    "model.layers.35.ffn_norm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.36.attention.wo.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.attention.wqkv.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.attention_norm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.feed_forward.w2.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.feed_forward.w3.weight": "model-00016-of-00021.safetensors",
+    "model.layers.36.ffn_norm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.attention.wo.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.attention.wqkv.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.attention_norm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.feed_forward.w2.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.feed_forward.w3.weight": "model-00016-of-00021.safetensors",
+    "model.layers.37.ffn_norm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.38.attention.wo.weight": "model-00016-of-00021.safetensors",
+    "model.layers.38.attention.wqkv.weight": "model-00016-of-00021.safetensors",
+    "model.layers.38.attention_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.38.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
+    "model.layers.38.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
+    "model.layers.38.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
+    "model.layers.38.ffn_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.attention.wo.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.attention.wqkv.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.attention_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.feed_forward.w1.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
+    "model.layers.39.ffn_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.4.attention.wo.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.attention.wqkv.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.feed_forward.w1.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.40.attention.wo.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.attention.wqkv.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.attention_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.feed_forward.w1.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
+    "model.layers.40.ffn_norm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.41.attention.wo.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.attention.wqkv.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.attention_norm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.feed_forward.w2.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.feed_forward.w3.weight": "model-00018-of-00021.safetensors",
+    "model.layers.41.ffn_norm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.attention.wo.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.attention.wqkv.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.attention_norm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.feed_forward.w2.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.feed_forward.w3.weight": "model-00018-of-00021.safetensors",
+    "model.layers.42.ffn_norm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.43.attention.wo.weight": "model-00018-of-00021.safetensors",
+    "model.layers.43.attention.wqkv.weight": "model-00018-of-00021.safetensors",
+    "model.layers.43.attention_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.43.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
+    "model.layers.43.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
+    "model.layers.43.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
+    "model.layers.43.ffn_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.attention.wo.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.attention.wqkv.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.attention_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.feed_forward.w1.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
+    "model.layers.44.ffn_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.attention.wo.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.attention.wqkv.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.attention_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.feed_forward.w1.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
+    "model.layers.45.ffn_norm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.46.attention.wo.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.attention.wqkv.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.attention_norm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.feed_forward.w1.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.feed_forward.w2.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.feed_forward.w3.weight": "model-00020-of-00021.safetensors",
+    "model.layers.46.ffn_norm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.attention.wo.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.attention.wqkv.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.attention_norm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.feed_forward.w1.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.feed_forward.w2.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.feed_forward.w3.weight": "model-00020-of-00021.safetensors",
+    "model.layers.47.ffn_norm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.5.attention.wo.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.attention.wqkv.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.feed_forward.w1.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.6.attention.wo.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.attention.wqkv.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.feed_forward.w2.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.attention.wo.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.attention.wqkv.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.feed_forward.w2.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.attention.wo.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.attention.wqkv.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.attention.wo.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.attention.wqkv.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.feed_forward.w1.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00005-of-00021.safetensors",
+    "model.norm.weight": "model-00020-of-00021.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00021.safetensors",
+    "output.weight": "model-00021-of-00021.safetensors"
+  }
+}

pytorch_model-00005-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e3b295c170c33adf209f507609fbec201a3534edd0ca2530d6524cc3dc63b989
-size 1963014163

pytorch_model-00006-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb3d4c2c9b32ac6e07eb649294497621e5511c244ba780b8476e3fa22b71ea6a
-size 1937823489

pytorch_model-00007-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:02c8539dc2ee3003f392001d61cd67a924fd6a4abdb6fddd70b366b703a8141c
-size 1963014227

pytorch_model-00008-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b7fe91599763599e612ff79bca50d1be9dd7cb9030d1e6dbacdb51dc45e22afa
-size 1937823489

pytorch_model-00009-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df8dae357eb00345ef42506045de1723869dabe8cf89fa192e06137cf3cd395d
-size 1963014227

pytorch_model-00010-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8add13dc25f54db6df0a8b5e8135a63f670ac7bcbcb5706b541daa96bdfdd6c
-size 1937823489

pytorch_model-00011-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32af852ccb9936da7d332e22beda929de7fcb1f96c39262b836bca387fe0161d
-size 1963014227

pytorch_model-00012-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ff97793ae1fe4d27af4f9209fbf2e532cd4fb1ccc39e399aa2f58bddb765f186
-size 1937823489

pytorch_model-00013-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c08ce8a307fa5fa3caebff931e1bf540e861e2fa38b1bfa4bcf91f7277e10
-size 1963014227

pytorch_model-00014-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15ebf9dcba9bd6b42c165736792b2ebdc33840bffc65c4314a0c704e34917d9e
-size 1937823489

pytorch_model-00015-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e353fef3f3a242e8e5af05afca8e5113582d7ea3225fbe1ce111e32816e48a2c
-size 1963014227

pytorch_model-00016-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ade1ad7844c0523e10e50cf541e20becd8d0a011305a0b5d49becc94cdf6692a
-size 1937823489

pytorch_model-00017-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d969e5162667a98b6ed514bbf8a92f611994673ff47155a526b0092863ebc6e9
-size 1963014227

pytorch_model-00018-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a8721d0d742ce15ae0f3081249b7cd7bb907701ee543101979d297cd9d6120f
-size 1937823489

pytorch_model-00019-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15b81635b5847683c9c943f8d819c29934a01e5a9e00a99464d8c5c3564d2938
-size 1963014227

pytorch_model-00020-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4d0dc96e4be3de25d042446799c96aa3bfb5204132cfe1d48db6f456aaf79bb1
-size 1560347805

pytorch_model-00021-of-00021.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1783c28825d2881dd23254e19422472464fdcd28416c9d9ae79b4fb46911ca1b
-size 1137181610

pytorch_model.bin.index.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e110c305db80b79307dbccd08c7e923304c1deff95dc6460ea62b7fa74716f46
-size 27171

special_tokens_map.json

@@ -7,8 +7,32 @@
     "<|interpreter|>",
     "<|plugin|>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenization_internlm2_fast.py

@@ -56,14 +56,14 @@ class InternLM2Converter(SpmConverter):
         return unk_id
 
     def decoder(self, replacement, add_prefix_space):
-        decoders_sequence = [
-            decoders.Replace("▁", " "),
-            decoders.ByteFallback(),
-            decoders.Fuse(),
-        ]
-        if self.proto.normalizer_spec.add_dummy_prefix:
-            decoders_sequence.append(decoders.Strip(content=" ", left=1))
-        return decoders.Sequence(decoders_sequence)
+        return decoders.Sequence(
+            [
+                decoders.Replace("▁", " "),
+                decoders.ByteFallback(),
+                decoders.Fuse(),
+                decoders.Strip(content=" ", left=1),
+            ]
+        )
 
     def tokenizer(self, proto):
         model_type = proto.trainer_spec.model_type

tokenizer_config.json

@@ -1,17 +1,6 @@
 {
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_internlm2.InternLM2Tokenizer",
-      "tokenization_internlm2_fast.InternLM2TokenizerFast"
-    ]
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "tokenizer_class": "InternLM2Tokenizer",
-  "unk_token": "<unk>",
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -37,48 +26,48 @@
       "single_word": false,
       "special": true
     },
-    "92543": {
-      "content": "<|im_start|>",
+    "92538": {
+      "content": "<|plugin|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92542": {
-      "content": "<|im_end|>",
+    "92539": {
+      "content": "<|interpreter|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92541": {
-      "content": "<|action_start|>",
+    "92540": {
+      "content": "<|action_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92540": {
-      "content": "<|action_end|>",
+    "92541": {
+      "content": "<|action_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92539": {
-      "content": "<|interpreter|>",
+    "92542": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "92538": {
-      "content": "<|plugin|>",
+    "92543": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -94,5 +83,20 @@
     "<|interpreter|>",
     "<|plugin|>"
   ],
-  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
-}
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_internlm2.InternLM2Tokenizer",
+      "tokenization_internlm2_fast.InternLM2TokenizerFast"
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "decode_with_prefix_space": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": null,
+  "tokenizer_class": "InternLM2Tokenizer",
+  "unk_token": "<unk>"
+}