Model Files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/kinqsradio/.cache/modelscope/hub/AI-ModelScope/gemma-7b-it",
+  "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_scaling": null,
+  "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 sha256:2fd94bdaab8cda14f29b2a9933115ccad1105864f6f1a1167c061b8a2592a450
+size 1572864144

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb903218c121e8a60ed53dd60ec05d06e07973a0880fba17eed7b49de3f3a9f
+size 956315336

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a42c61e9cd2cf16d4d0551171bbf13b3974a5c8880d46b9d3f15eaa7d635e7
+size 956327848

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ffe54ab44e5ea6e660208bf143a52256f9f8683ed143a5b2ca6e438ad6cb328
+size 956327848

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7997c12b4d263bd4a5eae74f751fca1c04e296249deb12cda180a4b988efe5
+size 855651576

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2077b9f47d1457c9981ff7851be7ea89c84a5bbe8200294a53363329da780348
+size 956327848

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b8e93bae3294d40fb861de1219cbaf86215a370f9f78cce8e8182b89397a00
+size 956327856

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d3b1a980a89fc7734dfea75ff222a3637083f348eb921c4f2265d41eb81e99
+size 855651592

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6170a558780d355bf02f09c4cc5359ef7460d5246f361884303922f8a0cbca
+size 956327864

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d17105f1cc4a0d93d45d13d3716211fbe334493cae56c194840ce3595784ff
+size 956327864

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aadc9bfc93fbcbd7be1bf30e4be217e7e99d09880c184d2e56454e55b987fcf8
+size 855651592

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a0705567ea37cccc5f95777442843307fc05e3384ad39b1a69c8d2800d5120
+size 956327864

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629e82fad5dd0cfc5e897b443ed5c97598096398d34f2b7a883269c3066dadc8
+size 956327864

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4980a26e8511a40f0d3e205c6391d773fd219e88f2557d0afc0715e64b5ad12
+size 855651592

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e768d74a3a8a3e250e19aec7fce22bcf1982b77a47aea51cf4b0bb5e3b534c3
+size 956327864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6510f09ec67d15c00dc03e8447107a9ccfd71ebe3917ef9f890363edb1ad41
+size 956327864

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b2a7a30182b470c0b9120ca2668c19b10d3b41e01337a5e2f766dafd597f11
+size 855651592

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35c036cf9bd3071ef7801fc0cc190974f43e7bb227a986707d4512ce58cfb12
+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 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "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.model

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

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "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
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}