Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 131072
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcd822089dc4fff62e0745cc17e2f24e85eaa36a1e45332dc51b5afb8825ed1
+size 4991309496

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cac6d2f48d620ac7767d851dcb1290743caeec2f9e65dd810e05a9e9d2d149a
+size 4928417048

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec98ef72d2b9086141aa2703807f2a28b3ad3464f94bd9cbebf42cefb6b10d4
+size 4928417080

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1849f8c2f6f64ce61ffb92ecde896ce0bb2a5983c8c21e978fbe36a3ea72c1f7
+size 4928417104

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4f2dddaa753f74a08e6b0d6bd505500f64c039ab806faf31e4e7d80aea0c
+size 4928417104

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734b001bca860e0718346af1bcd033a1f1968136ef73f1c7af0370beb1eab0c9
+size 4928417104

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e84d3ced7fff514a7774e5b5d768ea504156cd012aace486ce5be00b104fec
+size 4928417104

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9edd0d72d5c7244ac950d4577ddf4cfbc7a466a96b4644000be9e44a1a07ea
+size 4928417104

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df1da2bb80e4737854a8d850e2919a59f3934e9008c6db2b6401da88ff1bd6a
+size 2622296688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 42112460800}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors", "lm_head.weight": "model-00009-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
+size 17078444