Add 6B model, trained 26B tokens

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "RwkvForCausalLM"
+  ],
+  "attention_hidden_size": 4096,
+  "bos_token_id": 0,
+  "context_length": 1024,
+  "eos_token_id": 0,
+  "hidden_size": 4096,
+  "intermediate_size": 16384,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "rwkv",
+  "num_hidden_layers": 28,
+  "rescale_every": 6,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4f63423db6410b771d30e5948a65fa09fe9a5b88114265887afb7bee00faa4
+size 986367416

model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672262c483ed49990cde968358a7cd70d43f58d951067c6021e0ae149cfd375b
+size 939706432

model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b25f4db8deb7e6b298d030c10360cd3226693faf68fef5ad262a1f800af57b
+size 939739432

model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca08dffb28de491c9c316e7d1297ba4c233f225293cdc2e4aaad7cce1af8144
+size 872597456

model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133840ef0db0a26f640ca6512aac3c6f4d539db1a592126a09e1e9c98741f53b
+size 872597456

model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3032ff429aae9ef1befa08c99f70726e7af995472a0117fd8b5df4844b4cfe9e
+size 872597456

model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d743be3da793ccdc0efc4c2ae0f65d96e8d9e32571cf3c3adcdec67b435adcd
+size 872597456

model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62474fc419e8d6ecacdeef0ab2e6fffa81bc2fdc8058318c0e73d7f4d11669f9
+size 872597456

model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77255efe8aae17d6f41e2ec630084f9924f2d0480ffeba044e7095e36966b3c8
+size 872597456

model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ab6966a250da281e14c0ef010b6ba798d11466a73d78844fcd7f31da20fc12
+size 872597456

model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97589dc7f67d3044d51b52e4afa50508d39d1657806656c85e997b75d41c6c8e
+size 872597472

model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089033c637006d161d2c254eb4e5f7dd1c4ca70cdad3b45e2fd945d00d671b6a
+size 872597472

model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1ff9c98f8340d9b878daf58ca8472a492624a6e8e21cf91b92006c198364a7
+size 872597472

model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f8c4166ebfcce5d8164f7adc147795c258b3ef578330d90f36d4071a45004f
+size 872597472

model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5aa8930fdd083fdcad3a3d199f18e81f5c4db28fc962188b179e63de3f8add
+size 872597472

model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41946697b4c808642b7b56820c2e6db60fa75f80d251cff216ac94b45b146c44
+size 872597472

model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79780b75b6702a3420938d9c1b3234a7b49fb1298e6911d0ac2e207969161af6
+size 872597472

model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea53e10412634e185e6611c33c2ca1bb74af90763c61def3eda35b7c71713bb
+size 872597472

model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8ffbf15fa367293173d95d80d2e8e8dffd23f89e3fa4dd39c2b378a42b8d69
+size 872597472

model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423adb5eece064db2b3b8027c93b46eebf7ba6669d853654e699a3c66589511c
+size 872597472

model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6d5c7ea85da6a649318d29ad07b8946b26f0004350728ac692f3e6246575ed
+size 872597472

model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721248c42a43d51036833af75892a267c563de853cd7344653973009c7a3075f
+size 872597472

model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3326b3d2ba5b317d8d12d1cf109b34fd1ba3b7bef6811fb5d153315a5448f58e
+size 872597472

model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c897dbabf8e8d36a76848474fc1689f584ced3c44dffc5f3192f5fe843fc1c
+size 872597472

model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27258823aed4f076f26a8bd6fd2da20c969ab9ef2ace22cacfb5d6b2f6480d26
+size 872597472

model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee766974cc062d0505d4b7de4c1088c74e85e6b3fb72affb396ea8132c9a353
+size 872597472

model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2640b8488650c0b63b62f8eb028efb32ed13746755bb5c5bcacaf97481bb78f
+size 872597472

model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bc95495f80029c3440675c9597e6c278506e724bb400824f8fa29b12c9b512
+size 872597472

model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2547f98539cb0a722e148cac85db7c604f2c20b03abfc395b289a5d8882b9216
+size 604013112

model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19df539dfe3f36742987ba8428521fe1a5e4a4ec9de9f5325afd57e53714bd0d
+size 851968120

model.safetensors.index.json

@@ -0,0 +1,517 @@
+{
+  "metadata": {
+    "total_size": 26136674304
+  },
+  "weight_map": {
+    "head.weight": "model-00030-of-00030.safetensors",
+    "rwkv.blocks.0.attention.key.weight": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.output.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.attention.receptance.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.attention.time_decay": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.time_first": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.time_mix_key": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.time_mix_receptance": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.time_mix_value": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.attention.value.weight": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.feed_forward.key.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.feed_forward.receptance.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.feed_forward.time_mix_key": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.feed_forward.time_mix_receptance": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.feed_forward.value.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.0.ln1.bias": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.ln1.weight": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.ln2.bias": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.ln2.weight": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.pre_ln.bias": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.0.pre_ln.weight": "model-00001-of-00030.safetensors",
+    "rwkv.blocks.1.attention.key.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.output.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.attention.receptance.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.time_decay": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.time_first": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.time_mix_key": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.time_mix_receptance": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.time_mix_value": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.attention.value.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.feed_forward.key.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.feed_forward.receptance.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.feed_forward.time_mix_key": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.feed_forward.time_mix_receptance": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.feed_forward.value.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.1.ln1.bias": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.ln1.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.ln2.bias": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.1.ln2.weight": "model-00002-of-00030.safetensors",
+    "rwkv.blocks.10.attention.key.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.output.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.receptance.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.time_decay": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.time_first": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.time_mix_key": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.time_mix_receptance": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.time_mix_value": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.attention.value.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.feed_forward.key.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.10.feed_forward.receptance.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.10.feed_forward.time_mix_key": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.feed_forward.time_mix_receptance": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.feed_forward.value.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.10.ln1.bias": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.ln1.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.ln2.bias": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.10.ln2.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.11.attention.key.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.output.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.receptance.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.time_decay": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.time_first": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.time_mix_key": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.time_mix_receptance": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.time_mix_value": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.attention.value.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.feed_forward.key.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.11.feed_forward.receptance.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.11.feed_forward.time_mix_key": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.feed_forward.time_mix_receptance": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.feed_forward.value.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.11.ln1.bias": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.ln1.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.ln2.bias": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.11.ln2.weight": "model-00012-of-00030.safetensors",
+    "rwkv.blocks.12.attention.key.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.output.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.receptance.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.time_decay": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.time_first": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.time_mix_key": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.time_mix_receptance": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.time_mix_value": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.attention.value.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.feed_forward.key.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.12.feed_forward.receptance.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.12.feed_forward.time_mix_key": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.feed_forward.time_mix_receptance": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.feed_forward.value.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.12.ln1.bias": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.ln1.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.ln2.bias": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.12.ln2.weight": "model-00013-of-00030.safetensors",
+    "rwkv.blocks.13.attention.key.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.output.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.receptance.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.time_decay": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.time_first": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.time_mix_key": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.time_mix_receptance": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.time_mix_value": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.attention.value.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.feed_forward.key.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.13.feed_forward.receptance.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.13.feed_forward.time_mix_key": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.feed_forward.time_mix_receptance": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.feed_forward.value.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.13.ln1.bias": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.ln1.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.ln2.bias": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.13.ln2.weight": "model-00014-of-00030.safetensors",
+    "rwkv.blocks.14.attention.key.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.output.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.receptance.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.time_decay": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.time_first": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.time_mix_key": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.time_mix_receptance": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.time_mix_value": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.attention.value.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.feed_forward.key.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.14.feed_forward.receptance.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.14.feed_forward.time_mix_key": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.feed_forward.time_mix_receptance": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.feed_forward.value.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.14.ln1.bias": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.ln1.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.ln2.bias": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.14.ln2.weight": "model-00015-of-00030.safetensors",
+    "rwkv.blocks.15.attention.key.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.output.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.receptance.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.time_decay": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.time_first": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.time_mix_key": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.time_mix_receptance": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.time_mix_value": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.attention.value.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.feed_forward.key.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.15.feed_forward.receptance.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.15.feed_forward.time_mix_key": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.feed_forward.time_mix_receptance": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.feed_forward.value.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.15.ln1.bias": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.ln1.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.ln2.bias": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.15.ln2.weight": "model-00016-of-00030.safetensors",
+    "rwkv.blocks.16.attention.key.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.output.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.receptance.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.time_decay": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.time_first": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.time_mix_key": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.time_mix_receptance": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.time_mix_value": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.attention.value.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.feed_forward.key.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.16.feed_forward.receptance.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.16.feed_forward.time_mix_key": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.feed_forward.time_mix_receptance": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.feed_forward.value.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.16.ln1.bias": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.ln1.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.ln2.bias": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.16.ln2.weight": "model-00017-of-00030.safetensors",
+    "rwkv.blocks.17.attention.key.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.output.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.receptance.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.time_decay": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.time_first": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.time_mix_key": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.time_mix_receptance": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.time_mix_value": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.attention.value.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.feed_forward.key.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.17.feed_forward.receptance.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.17.feed_forward.time_mix_key": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.feed_forward.time_mix_receptance": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.feed_forward.value.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.17.ln1.bias": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.ln1.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.ln2.bias": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.17.ln2.weight": "model-00018-of-00030.safetensors",
+    "rwkv.blocks.18.attention.key.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.output.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.receptance.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.time_decay": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.time_first": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.time_mix_key": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.time_mix_receptance": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.time_mix_value": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.attention.value.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.feed_forward.key.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.18.feed_forward.receptance.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.18.feed_forward.time_mix_key": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.feed_forward.time_mix_receptance": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.feed_forward.value.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.18.ln1.bias": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.ln1.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.ln2.bias": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.18.ln2.weight": "model-00019-of-00030.safetensors",
+    "rwkv.blocks.19.attention.key.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.output.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.receptance.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.time_decay": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.time_first": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.time_mix_key": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.time_mix_receptance": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.time_mix_value": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.attention.value.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.feed_forward.key.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.19.feed_forward.receptance.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.19.feed_forward.time_mix_key": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.feed_forward.time_mix_receptance": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.feed_forward.value.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.19.ln1.bias": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.ln1.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.ln2.bias": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.19.ln2.weight": "model-00020-of-00030.safetensors",
+    "rwkv.blocks.2.attention.key.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.output.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.receptance.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.time_decay": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.time_first": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.time_mix_key": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.time_mix_receptance": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.time_mix_value": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.attention.value.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.feed_forward.key.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.2.feed_forward.receptance.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.2.feed_forward.time_mix_key": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.feed_forward.time_mix_receptance": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.feed_forward.value.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.2.ln1.bias": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.ln1.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.ln2.bias": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.2.ln2.weight": "model-00003-of-00030.safetensors",
+    "rwkv.blocks.20.attention.key.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.output.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.receptance.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.time_decay": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.time_first": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.time_mix_key": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.time_mix_receptance": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.time_mix_value": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.attention.value.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.feed_forward.key.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.20.feed_forward.receptance.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.20.feed_forward.time_mix_key": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.feed_forward.time_mix_receptance": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.feed_forward.value.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.20.ln1.bias": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.ln1.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.ln2.bias": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.20.ln2.weight": "model-00021-of-00030.safetensors",
+    "rwkv.blocks.21.attention.key.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.output.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.receptance.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.time_decay": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.time_first": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.time_mix_key": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.time_mix_receptance": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.time_mix_value": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.attention.value.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.feed_forward.key.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.21.feed_forward.receptance.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.21.feed_forward.time_mix_key": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.feed_forward.time_mix_receptance": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.feed_forward.value.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.21.ln1.bias": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.ln1.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.ln2.bias": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.21.ln2.weight": "model-00022-of-00030.safetensors",
+    "rwkv.blocks.22.attention.key.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.output.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.receptance.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.time_decay": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.time_first": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.time_mix_key": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.time_mix_receptance": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.time_mix_value": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.attention.value.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.feed_forward.key.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.22.feed_forward.receptance.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.22.feed_forward.time_mix_key": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.feed_forward.time_mix_receptance": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.feed_forward.value.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.22.ln1.bias": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.ln1.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.ln2.bias": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.22.ln2.weight": "model-00023-of-00030.safetensors",
+    "rwkv.blocks.23.attention.key.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.output.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.receptance.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.time_decay": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.time_first": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.time_mix_key": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.time_mix_receptance": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.time_mix_value": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.attention.value.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.feed_forward.key.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.23.feed_forward.receptance.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.23.feed_forward.time_mix_key": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.feed_forward.time_mix_receptance": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.feed_forward.value.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.23.ln1.bias": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.ln1.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.ln2.bias": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.23.ln2.weight": "model-00024-of-00030.safetensors",
+    "rwkv.blocks.24.attention.key.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.output.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.receptance.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.time_decay": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.time_first": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.time_mix_key": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.time_mix_receptance": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.time_mix_value": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.attention.value.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.feed_forward.key.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.24.feed_forward.receptance.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.24.feed_forward.time_mix_key": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.feed_forward.time_mix_receptance": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.feed_forward.value.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.24.ln1.bias": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.ln1.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.ln2.bias": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.24.ln2.weight": "model-00025-of-00030.safetensors",
+    "rwkv.blocks.25.attention.key.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.output.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.receptance.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.time_decay": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.time_first": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.time_mix_key": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.time_mix_receptance": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.time_mix_value": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.attention.value.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.feed_forward.key.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.25.feed_forward.receptance.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.25.feed_forward.time_mix_key": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.feed_forward.time_mix_receptance": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.feed_forward.value.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.25.ln1.bias": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.ln1.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.ln2.bias": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.25.ln2.weight": "model-00026-of-00030.safetensors",
+    "rwkv.blocks.26.attention.key.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.output.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.receptance.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.time_decay": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.time_first": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.time_mix_key": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.time_mix_receptance": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.time_mix_value": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.attention.value.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.feed_forward.key.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.26.feed_forward.receptance.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.26.feed_forward.time_mix_key": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.feed_forward.time_mix_receptance": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.feed_forward.value.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.26.ln1.bias": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.ln1.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.ln2.bias": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.26.ln2.weight": "model-00027-of-00030.safetensors",
+    "rwkv.blocks.27.attention.key.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.output.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.receptance.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.time_decay": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.time_first": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.time_mix_key": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.time_mix_receptance": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.time_mix_value": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.attention.value.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.feed_forward.key.weight": "model-00029-of-00030.safetensors",
+    "rwkv.blocks.27.feed_forward.receptance.weight": "model-00029-of-00030.safetensors",
+    "rwkv.blocks.27.feed_forward.time_mix_key": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.feed_forward.time_mix_receptance": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.feed_forward.value.weight": "model-00029-of-00030.safetensors",
+    "rwkv.blocks.27.ln1.bias": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.ln1.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.ln2.bias": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.27.ln2.weight": "model-00028-of-00030.safetensors",
+    "rwkv.blocks.3.attention.key.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.output.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.receptance.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.time_decay": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.time_first": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.time_mix_key": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.time_mix_receptance": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.time_mix_value": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.attention.value.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.feed_forward.key.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.3.feed_forward.receptance.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.3.feed_forward.time_mix_key": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.feed_forward.time_mix_receptance": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.feed_forward.value.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.3.ln1.bias": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.ln1.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.ln2.bias": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.3.ln2.weight": "model-00004-of-00030.safetensors",
+    "rwkv.blocks.4.attention.key.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.output.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.receptance.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.time_decay": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.time_first": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.time_mix_key": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.time_mix_receptance": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.time_mix_value": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.attention.value.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.feed_forward.key.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.4.feed_forward.receptance.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.4.feed_forward.time_mix_key": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.feed_forward.time_mix_receptance": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.feed_forward.value.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.4.ln1.bias": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.ln1.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.ln2.bias": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.4.ln2.weight": "model-00005-of-00030.safetensors",
+    "rwkv.blocks.5.attention.key.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.output.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.receptance.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.time_decay": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.time_first": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.time_mix_key": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.time_mix_receptance": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.time_mix_value": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.attention.value.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.feed_forward.key.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.5.feed_forward.receptance.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.5.feed_forward.time_mix_key": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.feed_forward.time_mix_receptance": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.feed_forward.value.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.5.ln1.bias": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.ln1.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.ln2.bias": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.5.ln2.weight": "model-00006-of-00030.safetensors",
+    "rwkv.blocks.6.attention.key.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.output.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.receptance.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.time_decay": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.time_first": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.time_mix_key": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.time_mix_receptance": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.time_mix_value": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.attention.value.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.feed_forward.key.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.6.feed_forward.receptance.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.6.feed_forward.time_mix_key": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.feed_forward.time_mix_receptance": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.feed_forward.value.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.6.ln1.bias": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.ln1.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.ln2.bias": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.6.ln2.weight": "model-00007-of-00030.safetensors",
+    "rwkv.blocks.7.attention.key.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.output.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.receptance.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.time_decay": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.time_first": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.time_mix_key": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.time_mix_receptance": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.time_mix_value": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.attention.value.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.feed_forward.key.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.7.feed_forward.receptance.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.7.feed_forward.time_mix_key": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.feed_forward.time_mix_receptance": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.feed_forward.value.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.7.ln1.bias": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.ln1.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.ln2.bias": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.7.ln2.weight": "model-00008-of-00030.safetensors",
+    "rwkv.blocks.8.attention.key.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.output.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.receptance.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.time_decay": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.time_first": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.time_mix_key": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.time_mix_receptance": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.time_mix_value": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.attention.value.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.feed_forward.key.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.8.feed_forward.receptance.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.8.feed_forward.time_mix_key": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.feed_forward.time_mix_receptance": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.feed_forward.value.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.8.ln1.bias": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.ln1.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.ln2.bias": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.8.ln2.weight": "model-00009-of-00030.safetensors",
+    "rwkv.blocks.9.attention.key.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.output.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.receptance.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.time_decay": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.time_first": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.time_mix_key": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.time_mix_receptance": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.time_mix_value": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.attention.value.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.feed_forward.key.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.9.feed_forward.receptance.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.9.feed_forward.time_mix_key": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.feed_forward.time_mix_receptance": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.feed_forward.value.weight": "model-00011-of-00030.safetensors",
+    "rwkv.blocks.9.ln1.bias": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.ln1.weight": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.ln2.bias": "model-00010-of-00030.safetensors",
+    "rwkv.blocks.9.ln2.weight": "model-00010-of-00030.safetensors",
+    "rwkv.embeddings.weight": "model-00001-of-00030.safetensors",
+    "rwkv.ln_out.bias": "model-00029-of-00030.safetensors",
+    "rwkv.ln_out.weight": "model-00029-of-00030.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<|sep|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}