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": 3, "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 sha256:4ba14f1b364666c588814c18fba54153a0115938361779a7cb6dbe4d39cf807f
+size 2543914800

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a7a6d396eb7009c09d33422893149fd92d593457a70743ecb7e8a5cc438542
+size 1929465360

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da62d4c378714861f3764f92d96f1cd1bf88296464b86e804c689e40c5cc6b4
+size 1577143448

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa825f828bd38b0e6a7140e5b2e1a31006f8414556e261f8ae94ecfa0ebf6cf8
+size 2197859448

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d5af90f46393dc8d31326916b98c18f9d94f29c164b64e4b4e6f9f16d87b25
+size 2046906000

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406cff0527663908db24202d65ae41633c3e26749021ab34b1a7ff3bcf1bf7cc
+size 1812024736

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e04a2cf6f13d3b50b2e56516ac13d8ae8a2641ea6edbb9b64bc3f72610a7bde
+size 1845537536

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9c5f12f62a19f9d2a2fda924d294c44a3629f2faebbc1f986e402b1ff2d730
+size 2281787320

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333c74d052acf8fb8b962098a4b3bebf2134dddc4290682d13b71b5e53888010
+size 1929465384

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080bb417e30700244ada86b76727b465e24927cf22821924d818cace33695fa5
+size 1493215608

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b22312aa895fed1e726c447ce297a4253fa30f662cff614dfdd0cf4b5a67f80
+size 2281787320

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9fa0fa6084d8dfd57f412b03a5f11060f24c69bf458333f934de6e0d524189
+size 1929465384

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe7a6b00164316a82382e11711f202c9c69e3e60a9155330e4062334c4606ce
+size 1812024760

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971ab3ecfb75e4676bcd80cbf58d432e566501985ef6770c94c91aea46106736
+size 1962978184

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7daf9076bea877b1203021c3d03855707b565565597ec34ffe96caecdcbefc6e
+size 2281787320

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8065eb08bb1b169dbe49d6b4d52beb04de4e647defea260e58caa766793f0e71
+size 1812024744

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5be0826a8a73180876dd3eec585df259265a6e0252cfb022f4f52580067095f
+size 1610656248

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02da8251217e790d38e55e0ec0f2a75d4cdcaebb78720517df5680fab58c4bf6
+size 2281787320

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d8d91d0a1decf04400e504ee9f2fc1b7411faea987fd7f62c6e8f14fcf123a
+size 1403062672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 93405585408}, "weight_map": {"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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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 %}"
+}