Upload MixtralForCausalLM

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ko-mixtral-v1.3",
+  "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": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963c3dc6c9a6620e0b3136063a892d31a5f599b9d2d094b9027c04c93d3103d0
+size 4785869120

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379ea1ae1030554ac38c797b9d287e4e7e960f5108e11037feb99c3a1ed6a4a3
+size 4966257472

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0175c38d084fc116eb1192b6c954eeb06548cdcf97b7e3b0d555feb6000f37
+size 4966290464

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ad27a0009354151a53a6caace55f7f93a9d2aef80c8c282605d0fdfb578ac3
+size 4899181864

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e103b2c3c1be57badb9ff0f0d3547186cf3febe84c1ab1ab745826ef20a2877
+size 4966257512

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a1c44376ce3e37de5903711b58fdcb9ae3594a99c067dd7fe57c2fe4726c59
+size 4966257512

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1715683499a501626ba39182677f300fb91dff5c3f556947224c148cd73e50
+size 4966257512

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a87cd006d2a455cedab190480936daebf43f4258ee7e5054885d44d2e3e6296
+size 4966257512

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2ae7b938f9c44a88556ec587f623ffedea5964320e01d0963080314aea1bd1
+size 4966257512

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15543f428fb34a0c32c8c06ab41d2967053527282daada0f33d82faa4557618a
+size 4966290512

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae604078a06d897b06c5695dda496107e271167bc980c9023844398af1d2c4e
+size 2101430040

model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+  "metadata": {
+    "total_size": 51516555264
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.safetensors"
+  }
+}