Upload

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "MaziyarPanahi/Llama-3-8B-Instruct-v0.4",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_moe_config.yml

@@ -0,0 +1,60 @@
+
+base_model:  MaziyarPanahi/Llama-3-8B-Instruct-v0.4
+dtype: bfloat16
+gate_mode: hidden
+experts_per_token: 2
+experts:
+  - source_model:  Alsebay/L3-test-2
+    positive_prompts:
+      - "Imagine"
+      - "Create"
+      - "Envision"
+      - "Fantasize"
+      - "Invent"
+      - "Narrate"
+      - "Plot"
+      - "Portray"
+      - "Storytell"
+      - "Visualize"
+      - "Describe"
+      - "Develop"
+      - "Forge"
+      - "Craft"
+      - "Conceptualize"
+      - "Dream"
+      - "Concoct"
+      - "Characterize"
+    negative_prompts:
+      - "Analyze"
+      - "Critique"
+      - "Dissect"
+      - "Explain"
+      - "Clarify"
+      - "Interpret"
+  - source_model: Sao10K/L3-8B-Stheno-v3.2
+    positive_prompts:
+      - "Dramatize"
+      - "Embody"
+      - "Illustrate"
+      - "Perform"
+      - "Roleplay"
+      - "Simulate"
+      - "Stage"
+      - "Unfold"
+      - "Weave"
+      - "Design"
+      - "Outline"
+      - "Script"
+      - "Sketch"
+      - "Spin"
+      - "Depict"
+      - "Render"
+      - "Fashion"
+      - "Conceive"
+    negative_prompts:
+      - "Divert"
+      - "Obscure"
+      - "Overstate"
+      - "Undermine"
+      - "Misinterpret"
+      - "Skew"

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccb52b4fd57f5da29b515b195b602366a103c5ce21a6b326f3fb20b68d948bb
+size 1050681576

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d924c781019332fc03ad7c3278bea611d87c59894df2f62429f6b82035d75a
+size 1990464144

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2374e8845c90bb183fed3950dbf511885ae9f5304f554b39f507b68f75b6ea02
+size 1996490952

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ab077ee5447c8b2a6a4e09f5a7676c51e9c4b2ee667a03878cbc21ad76a7d7
+size 1996490968

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914708a8ce17a09dbe4685ad2b0f39f492812e2fe31e4a0ddc0015635208faba
+size 1996490968

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8c468e502366da10836f21db58f62672f668907e2f85e00e98ee9818839fa9
+size 1996490952

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebc5b504a6525d9338a23a034d392724de390c59ee01f716586152b4bee8747
+size 1996490960

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702ec1c010ceab776dcae4968a1d0808051f4ba96ccb1935f1a73afc4ed9827c
+size 1996490968

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba363f01d08c0e6fd47e3ac317e489e8341f241bbb014386a94b6d8b64063dc
+size 1996490968

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb60b1493a0a0c64eefd24abfa1238b6dc897df9022f7af2bac919ad3c8496e
+size 1996490952

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec1597e03e57b29559c83850d967b4fd2575a51be6cc8c271e00ec6789ed5fd
+size 1996490960

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f411fddf547ecde9178c0d11c24bdaab48332d334d3e8c6e3450c069ba83d0b0
+size 1996490968

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc48c547c0d61aa02622e33664c05ad40b34ceff93ca840e96a064d0f29aa05
+size 1979980448

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb974ec9c4de866cba5106bec68345791cbc14071c972dc541ed4de0b0b9696
+size 1979724008

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b41e15faf4653e59c162d1a2d617a9b51ec1a2c1dbb9333084679869c7e250
+size 369628008

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.norm.weight": "model-00001-of-00015.safetensors", "lm_head.weight": "model-00002-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|begin_of_text|>"
+}