Upload folder using huggingface_hub

README.md

@@ -0,0 +1,41 @@
+---
+base_model:
+- meetkai/functionary-medium-v2.4
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [meetkai/functionary-medium-v2.4](https://huggingface.co/meetkai/functionary-medium-v2.4)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 10]
+    model: meetkai/functionary-medium-v2.4
+- sources:
+  - layer_range: [5, 20]
+    model: meetkai/functionary-medium-v2.4
+- sources:
+  - layer_range: [25, 30]
+    model: meetkai/functionary-medium-v2.4
+merge_method: passthrough
+dtype: float16
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|content|>": 32002,
+  "<|from|>": 32000,
+  "<|recipient|>": 32001,
+  "<|stop|>": 32003
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "meetkai/functionary-medium-v2.4",
+  "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": 30,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 8192,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 32004
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+slices:
+- sources:
+  - layer_range: [0, 10]
+    model: meetkai/functionary-medium-v2.4
+- sources:
+  - layer_range: [5, 20]
+    model: meetkai/functionary-medium-v2.4
+- sources:
+  - layer_range: [25, 30]
+    model: meetkai/functionary-medium-v2.4
+merge_method: passthrough
+dtype: float16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6e64fae6724f009cc28eaf3b96cacf00c0eefc3cc8ec39db444482c6d29678
+size 9976510240

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af26dd380a6d8d359b7efd174b3fb6f9b3a30611fccb922e4f06a703ebebfe9
+size 9949296136

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911f132b95d9a320bae4e577afa745426602d8c7c8cceba004960b4e30d2402e
+size 9965974736

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7d8158eab393ac160fa7be929715fa2264550977ca59be286a176e911193b6
+size 9999496400

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196e5a84a82be249bae39a1fa7d57988cf705b84dd9b0165a9612befbc6403d0
+size 9915527616

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae0afeba0567cf8fd58e69acf7cbf59ba47309c3878b90f3e411969dc9e06fe
+size 9966008016

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2116fa7d9a923209e245b5dc9fb33b6ce6ee1020481d33d478bb41e42f9360f4
+size 9999496456

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89455d9e0c7818b7f39123eb43818e84fa541f2756f50165f5662bc35d8f06a
+size 9965991400

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f816059afd848e8a1adf48292d51f94338d4e05c9f31fc0b2c3dbc0798b2f70
+size 7862388360

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 87600570368}, "weight_map": {"model.layers.1.self_attn.o_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.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.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.1.w2.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.w3.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.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_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.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.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.1.w2.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.w3.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.0.w1.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_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.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.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.1.w2.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.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_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.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.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.1.w2.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.w3.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.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_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.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.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.1.w2.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.w3.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.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.o_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.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.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.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00009.safetensors", "lm_head.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<|from|>",
+    "<|recipient|>",
+    "<|content|>",
+    "<|stop|>"
+  ],
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|from|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|recipient|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|content|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|from|>",
+    "<|recipient|>",
+    "<|content|>",
+    "<|stop|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' or message['role'] == 'system' %}\n{{ '<|from|>' + message['role'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% elif message['role'] == 'tool' %}\n{{ '<|from|>' + message['name'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% else %}\n{% set contain_content='no'%}\n{% if message['content'] is not none %}\n{{ '<|from|>assistant\n<|recipient|>all\n<|content|>' + message['content'] }}{% set contain_content='yes'%}\n{% endif %}\n{% if 'tool_calls' in message and message['tool_calls'] is not none %}\n{% for tool_call in message['tool_calls'] %}\n{% set prompt='<|from|>assistant\n<|recipient|>' + tool_call['function']['name'] + '\n<|content|>' + tool_call['function']['arguments'] %}\n{% if loop.index == 1 and contain_content == \"no\" %}\n{{ prompt }}{% else %}\n{{ '\n' + prompt}}{% endif %}\n{% endfor %}\n{% endif %}\n{{ '<|stop|>\n' }}{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ '<|from|>assistant\n<|recipient|>' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 8192,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}