Upload folder using huggingface_hub

.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

README.md

@@ -1,3 +1,18 @@
----
-license: gemma
----
+---
+language:
+- ko
+- en
+license: other
+library_name: transformers
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+pipeline_tag: text-generation
+tags:
+- pytorch
+---
+
+## Model Details
+
+**This model is fine-tuned by beomi/gemma-ko-7b**
+
+**Fine-tuning dataset: Scientific QA dataset**

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "DimensionSTP/gemma-ko-7b-scientificQA",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "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": "float32",
+  "transformers_version": "4.42.3",
+  "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": "4.38.1"
+}

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c92ca0c82debce542ec058bdc5a8d748f4deb45162f56e0e931160c5b2d6492
+size 6165678928

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7300fa2242924406278a02a38a77131b8b9c1b1ed29d3869df929c259d659b0
+size 2717985608

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c382b4feab02a68f0065d17f8c08fc2c7bbfb25d0e27a886d90b2485fc2f90c5
+size 3221302080

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9b9e04b650d28881b89eb7c63975ba87d503cd9d3d4f1fddecf14069ca1920
+size 3221302088

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6438146775beee96ff8a642589c88f6f3236e76d4388fa64954f8a724c249a
+size 3321940832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1a464a61c895511cd0059857843503ee37fa92843298beac6f0d99e41be15a
+size 2717985616

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a84c2be4afaaabadbd83f0e5ed692fd72890cbe8e43d18e822d709559e001c3
+size 2969643872

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36de7c6d057351623fb54fb1a28022ffcbced72195624beb9e5b9044adcaec7
+size 3221302104

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd80d523cba3151d78beab63d5388fde85859d2fd9fe12ef39a1d2806411d6ad
+size 3271621464

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2d592de83bcb41f0b030f2b5004738ac2e9fb01af5a998ef848d67584e3d35
+size 3019963224

model.safetensors.index.json

@@ -0,0 +1,257 @@
+{
+  "metadata": {
+    "total_size": 37296451584
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00010.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 sha256:4db21bfaffa1fd75fd741df2d95dc51e539d5cc38b07934bae0d7d129db90662
+size 17477581

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
+}