Upload

README.md

@@ -0,0 +1,50 @@
+---
+base_model: []
+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:
+* /content/models/testing-method
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: "/content/models/testing-method"
+        layer_range: [0, 24]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: "/content/models/testing-method"
+        layer_range: [8, 24]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  - sources:
+      - model: "/content/models/testing-method"
+        layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "F:/content/models/testing-method",
+  "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": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+slices:
+  - sources:
+      - model: "/content/models/testing-method"
+        layer_range: [0, 24]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: "/content/models/testing-method"
+        layer_range: [8, 24]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  - sources:
+      - model: "/content/models/testing-method"
+        layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aaecb9d1f3f8410c0ce216fb33e361bbd38662199fce4632cb34595cdcd7478
+size 1900054960

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d306924b30fe5e15cab31a5a35bdb2fd2044dd5f87dfa45359926c6aa305fd6
+size 1895928016

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085884b70058c179e867e01a9ada6a94cc95d5e07be8846c21cecd1c9f9edaea
+size 1929449016

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa39d3438f21801dddbb20da2326d71a021f4c32ddf768b09e3760b5a04aa086
+size 1929449016

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc09d9e81c42eb30cedd07789242072f4b1ef15a0ef4da1523bec28cdb37c890
+size 1929449016

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ff5173ea9080d7fa4589366d3656ca3a6a65b2981a7ada2a33c0632eb7f575
+size 1979847704

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a688a21bd8ca7b1610b9844ec64251de10c711315d458104b9655300de0e9d
+size 1929449016

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40564d5eddb8c972168f1cc6a70d15aeffd9319e43dd3c1893ec3f25d0ba04be
+size 1929449016

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33c01c41303c2504bbbf78453f183e84969c7f781e800d0fb24e8078d561a66
+size 1929449016

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d1e6549de472946b8a75fb752ae1ab463e3ac943f409c879bf9dfd9eaf8c1c
+size 1895928032

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ef64acdca37996e6c3bdd82f9a72d88817fc50347b9fd473345bfd484ea416
+size 1929449016

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597096195f7b53fd037314960c49798b5d7fc45287cba9346e71319ab1080287
+size 1929449016

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4dfe7f48857acc731249644ce75bdafead21f26650ca47ecfe70b0f27ae291
+size 1979847696

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b77a679b5c8fd46dad79670f36207319ecec7b4e4002303467e51bf25841ac0
+size 1929449016

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88b7b571105568eb861733a0661b6e62ddb962d78ca3a4ba8edb44ebdf19ab2
+size 1895928040

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224e6a28220eb62929b89ad092b38a3a13d6a02f9f302f7e2e66a42aac16de93
+size 1929449000

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbecb1badf1b6f4b2f6227423829efb7393a15557c216d0b46ca8cd496bb9062
+size 1971425400

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bb3a28c45f9c22734d2630da09bc76d67113321d6d2c6e69ca0b1a742aa8a4
+size 1971392248

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29a9d85a7599e8629aef853cc8784b680cbc867ca7c5c9a4f1253e8fb51a81f
+size 1996591216

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c782eb60561aeec9ffeee7e6cf13eba84abc978d040be6be9b2a1bc94c935d
+size 1593912792

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 38375268352}, "weight_map": {"lm_head.weight": "model-00001-of-00020.safetensors", "model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "device_map": {
+    "": "cuda"
+  },
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 16384,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}