init

config.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 7, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.36.0.dev0", "use_cache": true, "vocab_size": 32000}

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbe0d44762028a61d90e070d4617315d766c6f86e4def7812393742a9d1a9af
+size 4188149336

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fc0b16a01c75b53c3cb41e16e634aafe3e86ed6aeb1c83bc300698d4a818a4
+size 4513225064

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7161cce9125bfdf410232cfb13b97a20e551318d66e312966fa135564c19d7
+size 4395784416

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b36839f9a697a38dec4ccc73c86609918f82bde67b5feafde243da065e4fc5b
+size 4194383152

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb4d8ea44236646886f493f4f1494251a31b9450dbba3771f81aded0ca44e5a
+size 4278343768

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4fc60a1d1a635e1459dd48a2873ddece68f04e65485bb76db32e6fb21d38bd
+size 4630665704

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19334f4a13da02f8bfabf825981a826424090fe32fe1eb3d7093de3e912a2c2e
+size 4194383192

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8010f846c84d929e466cfdb3e52babec174a6a19ef58da64d64a77ebdfbc5bee
+size 4278343824

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376314bcf72808576d0e72a94003033929bd08917f73b31a556f189b9c37e04e
+size 4630665760

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf4e13642ee71dbf5975da41d34f9e6e3ceed337d2eaf4d107bd4976db4962f
+size 4194383192

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8a0e52c04e2ca52cefb5cd257901672d792bae593ade747be38e594ac055cc
+size 4278343824

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd81d56dc82c0fc1419364ede4d541e548d3b4705e37f819050f601b3203a150
+size 4278343824

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97f3c924e495466062c5695a927c19a14efe86b3499a02c57e5c517d587db28
+size 4630665760

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c254d5facce7b085c746c9edb7bef2597648d48e2908baf70ef2455671e8fe2
+size 4194383192

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d20bf9805674cea95e6e22f2f63f9a1f05ff114bce784b55d942de15497fedd
+size 4278343824

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00667435d4633706cbf9386328c518d92d186ddb00b3b84c483f9f0e9b64d737
+size 4630665760

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af572531dc0ff793ae7398d49f0e52956197f2db31af3388c83aad3c98dc7f3d
+size 4194383192

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3231270926baf6ad7dac3e3a5648eafdf2bd1f6635eac66682e144606ff4683
+size 4278343824

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3c47ee4eb2b53d49eca67d3519e46f5fceb280726d5bd5bcf82643ecc0c9b1
+size 3869348968

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 93405585408}, "weight_map": {"model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "lm_head.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}