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": 5, "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 sha256:8530ddfb3c8a7eb4b32e4f6351af4218d314376ef584aa0d3d0fefe0d2ccc3bf
+size 3483472712

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0b7f984920c4ab9e31985579b3e8e77a945b0554a690554978f61f7c5fd8b1
+size 3103904576

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d55092bf921cf5aeb9b1d2f0f94b218ef51d4ce446d5291b12ef9a77f996341
+size 2986463936

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb95ec4d8869d2e0887a0486950468c28607b4f3970201e7381d160e506ad3b
+size 3254841624

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34ba7f4a36850510a9da29d1b6bea602d3c249b311c8d6950a1b4ff41af6d9b
+size 3103904576

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202d42e7ca88a5e895baa6a8084097c04fec99521beb4f233596133ac534adee
+size 3221345224

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5616b9919013d12c489fd0fa8164ff6a862663342d8141f5443f208ec2649d3
+size 2902519720

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f335bc06997c232ce582ef2c0271c677720d71b7dfc42eb9ad23b80f871006ad
+size 3456226544

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702d6453aae8a47712108098b36d18609df2b60389709adcd6a2c30a931dbe6d
+size 3221345256

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dad8fff7b42c245001d0471fbb922ecb30e5cc16342e3a91f3799b096c27539
+size 2785079080

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba0c6f4844c14446df992f2fc7db17e7de631662d3bbc7959e16ff4ac2669a0
+size 3456226544

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abff4c2e01cd569439912f0347e480ab708a0da7dbb3dd77835cb9ca2c3fd0b
+size 2986463968

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cab235b9314bce8a75d8b21022d0d7b3d37cc1937bfc1b994ba95f6025b2567
+size 3221345264

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ab75670832ab46415d753fec4340ff5017491f0a453564d1c710125adcf9e6
+size 3019960368

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d16815feed062df7196edde446f471ebbc5347470b7dea7e486f0ac9108a55
+size 3338785904

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967735f9c5137c31ed6e552be715af8187a9d741adcf9c9e5c5837f6829dff62
+size 3221345256

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3748ded4a665543df0a66224a170851d7688d5ec4ce771020ac24fe5992adc
+size 2785079080

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b479d73c182b4d5cc6365cd6bf17cae5572ab85cc4b9b75e4469e0a648974a
+size 3573667192

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f77afda53a1f59fa57bcfa01747c3e580e3eaf605f1697a2633d92a87d83ff1
+size 2460044848

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 93405585408}, "weight_map": {"model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.4.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.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.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.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.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.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.w1.weight": "model-00012-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.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.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.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.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.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.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.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.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.4.w1.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.4.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.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.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.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.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.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.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.4.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.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.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.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.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.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.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.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.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.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.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.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.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.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.4.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.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.4.w2.weight": "model-00018-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.4.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.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 %}"
+}