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": 4, "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:e954291677d51ecb6057c429ca4b3376e7b9838d7747057c61e807dc10cfad8b
+size 2896253112

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb865665601f29a76349384efc8f71e717f28b8358cc4dbd2b44c61b7410bb0a
+size 2634125616

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6838d2a7eb1238db6569a1b5d74a245a6edc4cf6220204d464c25fe673b417
+size 2281803688

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f07edea5c33ff230302dba36c915782f1569f4ac240839ca2c9322bdd1c1857
+size 2550189568

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d676f77eb94123a1fb9660f96a8a9820a7b23f43dac90b780bb338adf992d52
+size 2751566264

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d0f74c0af4fe81285382f6e414deb91368599061621cb7764444537360a122
+size 2516684976

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91200a76c65a94bc8b183dca70224e1da4631f8da939279ba4413e9086136237
+size 2197867664

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322aa8bcaf50e6b1e442275646d5382f58d17e53bccda470b9950ebba36687d3
+size 2986447584

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec1eab881470d4bb7a1dc8ede5d965a976dd66175511af03ba7ffba0b8050df
+size 2634125656

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d2949908e52f951ffc53999d3a73063a68e813e9749258bf8704085f1707c5
+size 2080427016

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff1fa1dc6b736e2541d606ab0dbf53bf46af0ffa99d76587192735513afc86b
+size 2751566296

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca74cba9813ce26a770316810b1e2aa9cc973055c12b590e6728121db7eab66a
+size 2634125656

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883f7c8f2812fe21a15e767ebf2e3a50699dfcb2a2243ded3b76eb928a402002
+size 2516685008

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f4898f057f39e52d7ee2ac978e7168eb0b59bba3a2807d2cb78c0fdfed60df
+size 2315308312

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940de80b2ff24a4d3dac41a90cb3fe093576b8e1013b142f304d4fada159a901
+size 2986447584

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5efd7a6e0035d54e59f2870e4edef5102c9e9748bd31cc475aa958539eef6f1
+size 2516685008

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5bfcfdd95d422cd677126866e93f9543ee07080905a6f613a579aceaf554af
+size 2080427016

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02938386655f3804080b9ff7022e849c685b8174936b2fa1758f6bba9a9e263
+size 2869006944

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66114b5b8087e24ab08250e7729465020b0a3f6efbcfd34e54851ecb1581bea5
+size 2107714728

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 93405585408}, "weight_map": {"model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.3.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.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.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.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.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.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.3.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.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.w1.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.3.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.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.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.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.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.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.3.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.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.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.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.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.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.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.w1.weight": "model-00009-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.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.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.3.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.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.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.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.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.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.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.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.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.3.w1.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.3.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.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.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.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.3.w1.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.3.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.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.3.w2.weight": "model-00018-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.3.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.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 %}"
+}