Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "LeroyDyer/Mixtral_AI_Cyber_5.0",
+  "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": 3,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,140 @@
+
+base_model: LeroyDyer/Mixtral_AI_Cyber_5.0
+gate_mode: hidden 
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts_per_token: 3
+experts:
+  - source_model: LeroyDyer/Mixtral_Cyber_BioMedic
+    positive_prompts:
+    - "Teacher"
+    - "Lesson"
+    - "Class"
+    - "Tutorial"
+    - "Study group"
+    - "Your a helpful assistant"
+    - "You are a AI assistant"
+    - "Medical"
+    - "Doctor"
+    - "Nurse"
+    - "hospital"
+    - "clinic"
+    - "help i dont feel well"
+    - "Patient"
+    - "Medicine"
+    - "Drugs"
+    - "Pharmacy"
+    - "Scientifc principle"
+    - "Medical"
+    - "Biological"
+    - "you are a doctor"
+    - "You are a nurse"
+    - "You are a lab assistant"
+    - "you are a pharmacologist"
+    - "You are a medic"
+    - "you are a virologist"
+    - "You are a psychologist"
+    - "you are a oncologist"
+  - source_model: LeroyDyer/Mixtral_AI_CyberCoder
+    positive_prompts:
+    - "create a program in rust"
+    - "Create a program in Go"
+    - "Create a database in "
+    - "Network"
+    - "White hat"
+    - "Hacking"
+    - "Snooping"
+    - "Scanning"
+    - "intercepting packets"
+    - "Network Traffic"
+    - "Brute Force"
+    - "Password"
+    - "Logging"
+    - "Keystrokes"
+    - "Automated Task"
+    - "Variable"
+    - "String"
+    - "Literal"
+    - "code"
+    - "Object Oriented"
+    - "Use-Case"
+    - "Deploy script"
+    - "Packet Injection"
+    - "Cyber"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "VB.NET"
+    - "create an aplication in"  
+    - "Write a functon to"
+    - "write a program to"
+    - "create a model in python"
+    - "create a model in javascript"
+    - "create a model in VB.NET"
+  - source_model: LeroyDyer/Mixtral_AI_CyberRolePlay
+    positive_prompts:
+    - "create an inner monologue"
+    - "create a monologue"
+    - "create a monologue about"
+    - "create a monologue of"
+    - "maintain an inner monologue"
+    - "maintain a monologue"
+    - "maintain a monologue about"
+    - "maintain a monologue of"
+    - "keep a log and record of events"
+    - "keep track of the project documentation"
+    - "play the role of a character"
+    - "you are a character"
+    - "you are a woman"
+    - "you are a man"
+    - "you are a boy"
+    - "you are a girl"
+    - "you are a animal"
+    - "you are a bacteria"
+    - "You are a Person"
+    - "You are a happy"
+    - "You are a sad"
+    - "You are a angry"
+    - "You are a tired"
+    - "You are a bored"
+    - "You are a timid"
+    - "You are a drunk"
+    - "You are a funny"
+    - "You are a intelligent"
+    - "You are a friendly"
+    - "You are a helpful"
+    - "You are a Person"
+    - "You are happy"
+    - "You are sad"
+    - "You are angry"
+    - "You are tired"
+    - "You are bored"
+    - "You are timid"
+    - "You are drunk"
+    - "You are funny"
+    - "You are intelligent"
+    - "You are friendly"
+    - "You are helpful" 
+    - "Feel like "
+    - "thinking of" 
+    - "Dreaming of"
+    - "Wondering about"
+    - "you love"
+    - "You hate" 
+  - source_model: LeroyDyer/Mixtral_AI_CyberLAW
+    positive_prompts:
+    - "reason"
+    - "lawyer"
+    - "Legal issue"
+    - "you are a lawyer"
+    - "count"
+    - "Court case"
+    - "legal problem"
+    - "affidavit"
+    - "affidavit of"
+    - "affidavit for"
+    - "Contract"
+    - "Contract for"
+    - "lease"
+    - "Agreement"
+    - "Publishing"
+    - "Agreement for"    

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7376ee0937c7717188635c5b92ff9485d8e04bf54e007d58a99bd93665579465
+size 5909856808

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027c6cbce86fb55f7a79522aa3c6ec5bcf7bbd18b34a54da11bd9c49f88154e7
+size 5972763536

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b2da02bfa47eafae1ed9c2acff295e0d391cce16d3c9086d0ffa7a653703a9
+size 5972763568

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629ea3893631a9b4d747dd422f313d0fb7e9d811c7216daaf1e48952dda3a930
+size 5972763608

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f1d655fa336956939c2be461146f5bb1ceab919c037d0c25aa1c069657f69f
+size 5972763608

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960c5abfc1ceb5643116f84a6e10ab4430e9561dbc31285ff6f63bf1e9a1161
+size 5972763608

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6945f4a079804744940ca5d0994f3c3d23edf2a28f56e62ff2187fbabb66d669
+size 5972763608

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da414be0170e515554c11382cba0eacc11c268e892532935464c812c7ad9c4fa
+size 5972763608

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca11bb5531f9798e04655c1f5dd2abb53c09e93f465eae2192742dbc3fea70e2
+size 588255432

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 48307380224}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.norm.weight": "model-00001-of-00009.safetensors", "lm_head.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}