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

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "beomi/gemma-ko-2b",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "mixtral",
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 256000
+}

mergekit_moe_config.yml

@@ -0,0 +1,10 @@
+
+base_model: beomi/gemma-ko-2b
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: beomi/gemma-ko-2b
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: google/gemma-2b
+    positive_prompts: ["You are helpful assistant."]
+  

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94615fd1cf9e642a64c3523df1d5a91434d8e29d71be69e080483c7645a7e950
+size 1048580328

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebc1e0b5efa418954292a5f553520968ab2e04d9302e8d3dbce74b2530faf7
+size 1977642800

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28274b93bae20a8202e03303c96cb451f2afbbb58568bcc51d99e42b36cc9685
+size 1954584832

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6665605d3144a0dac3dafe9d9272e558c8ebe9e357cd23c9045d007cad6c4c
+size 1973468088

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ede19ffebcc3f78350c850d2f1c071353ec3862953437497fb84e6b4256b06e
+size 1973468136

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e72c682d8cf9c996bebe2edbd9b212df5c3fd851c93024057f145c4155e0c5
+size 757231688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 9684946944}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.norm.weight": "model-00001-of-00006.safetensors", "lm_head.weight": "model-00002-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<bos>",
+  "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 sha256:16c7bb55a4086eff7c63d3a73bb0e92578ba318dee0a8b51f7fe128911268a7d
+size 17477707

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": "<bos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}