Release model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b3b46a28e430403e5e8106f0305c0b8af7689994bd3849106aae8025bec201
+size 1572864144

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad407243dcb1926974da87027516200810e6267825fb11c29ad0e3027af627e6
+size 956315336

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7889d991546ea0ef4adb4cf71b18b991f09daacbc0820e7e5ec9dedad991c672
+size 956327848

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d766ee7ef539eef40e74a59d3860a9a540c703ee37730c6fc8c460e356af61e5
+size 956327848

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da735efeac78bb4322d331e8040404636a95074bd217ddf60cd46d0a52434abe
+size 855651576

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3c5e1aa302f2fae41f1019c35606028a7621ae6f1b1b7b041a089f215b7e15
+size 956327848

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2faeeb0756ff7f033c3bb4a28eae631529c5a6f9759ada831b729415e5f580
+size 956327856

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b8db1c3c1a886eb5734a0cf8e2a75cc17ffdd437ef529383975668062dcc87
+size 855651592

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a233890d01a2f58739f4372576af9295cdfab07011a63a4093c79749fa1881de
+size 956327864

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d949a57ebed85718d8588ede28a8aada757fd9ece038d77a8c8c39aa71d840a6
+size 956327864

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec08a7a494fa5674df8f20d293a80998859faa518dbc2ae6fd221c300de780da
+size 855651592

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519a59230d4ce2a047966ce2f574b44c7eaa2a2410a4bf0ad80742a886e02362
+size 956327864

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3f9c68eead46ac36f9116f0d5be9aaa9d92e256bce25fd3931883094377925
+size 956327864

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5006b4f0e58f011bd4b15e15e7a66fba28d503ecb166d656a411afc3fb5037
+size 855651592

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24666aed6f215403d5fd53dce30e5fb840302d2a7456c42652360e866eff39ce
+size 956327864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c6b607742ba8ad052cf66e2c4fc70de5df68ad72e055b1bbee788b3c8a7f70
+size 956327864

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba90a8aee577677bb19265d871ca0798e108d001a2a7b29778cebae8985a6263
+size 855651592

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604b93cf4a5dec41f29a061e47e0c5b19ead6cc90ed9c16342f3e93ae182f565
+size 704675280

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.norm.weight": "model-00018-of-00018.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}