Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Undi95/Emerhyst-20B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 40,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,7 @@
+base_model: Undi95/Emerhyst-20B
+gate_mode: random
+experts:
+  - source_model: Undi95/Emerhyst-20B
+    positive_prompts: []
+  - source_model: Undi95/MLewd-ReMM-L2-Chat-20B
+    positive_prompts: []

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee08ed2fd0200d6d5e9bb99085a3ddb8efff831f198fce82a6ac8664505a135
+size 9998833088

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461804a99e690cf7668c0046b171d27f2eb6f65d018de93268c5be26fd80c50d
+size 9909052376

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be8010ae5d328acf17ad89a394b9b814f316dd29aa3c68d3ee9beab8247ef5c
+size 9909052384

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376fbbd012d7d4cee0700146d0bd9029a07e72e44b7e54abfabd7a02b091f3cf
+size 9909052368

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06906032c5e265253a334de96fc905beec14f6bef274cb640d203bd3a0981ecd
+size 9909052392

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ec9b25ab130ae73c9c6e0d9b8b8ebddc2b87c0bfd23af31d38edc42add8e36
+size 9972617464

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5d7d8d61ad9cdcac0f5796639ee4fbab5d1c85ebd45afee66feecd607134b4
+size 6712178448

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.60.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.61.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.60.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.61.block_sparse_moe.gate.weight": "model-00007-of-00007.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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}