Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "NeverSleep/Noromaid-7B-0.4-DPO",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 6,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": false,
+  "vocab_size": 32002
+}

mergekit_moe_config.yml

@@ -0,0 +1,55 @@
+base_model: NeverSleep/Noromaid-7B-0.4-DPO
+experts:
+  # Philosophy Expert 
+  - source_model: sayhan/OpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRA
+    positive_prompts:
+    - "Philosophically speaking, the nature of reality itself is called into question.*"
+    - "One could argue that the distinction lies in the fundamental difference between appearance and essence.*" 
+    - "To illustrate with an example, Plato's allegory of the cave speaks to our limited perceptions of truth.*"
+    - "The underlying premise the speaker presents is that knowledge is merely a recollection of what the soul knew prior to birth.*"
+    - "The crux of the matter pertains to the dichotomy between the ideal and the material realms.*"
+    
+  # General Expert
+  - source_model: Weyaxi/Einstein-v5-v0.2-7B
+    positive_prompts:
+    - "*I pull up my code editor and show you the Python script I wrote to control the snake,*" 
+    - "*The code to make the snake move continuously goes like this:*"  
+    - "*In Python, you can initialize the game board like this: board = [[0 for x in range(20)] for y in range(20)]*" 
+    - "*Here's the C# implementation for detecting if the snake has collided with itself or the walls:*"
+    - "*And here's a script to generate new food pieces at random locations:*"
+    
+  # Roleplay/Story Expert
+  - source_model: TeeZee/DarkSapling-7B-v2.0
+    positive_prompts:  
+    - "*With a gentle smile, I begin to describe how my character deftly maneuvers the snake through the maze.*"
+    - "*Leaning in closer, I whisper softly, 'Watch as the serpent stretches ever longer, hungering for that next delectable morsel.'*"
+    - "*My eyes meet yours as I respond in a somber tone, 'Though the serpent grows powerful, its greed may yet prove its undoing.'*" 
+    - "*Hesitating for a moment, I carefully choose my words, 'The path winds ever on, but where it leads, not even I can say...'*"
+    - "*A wistful expression crosses my face as I recall the serpent's humble beginnings, 'It seemed so small at first, but now...'*"
+    
+  # Medical Expert
+  - source_model: cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5
+    positive_prompts:
+    - "Coughing fitfully, their breathing grows increasingly labored as the venom courses through their veins.*"
+    - "Clutching their chest, they collapse to the floor, eyes wide with terror as the snake's fangs drip with deadly neurotoxin.*"
+    - "Bleeding profusely from the wound, they quickly lose consciousness despite my efforts to stem the fatal hemorrhaging.*"
+    - "Choking back tears, you feel them trembling under your hands as you try desperately to keep their airway clear of obstruction.*"
+    - "A red welt rises where the serpent struck them, blooming into an angry bruise as the potent venom takes hold.*"
+    
+  # Story/Descriptive Expert
+  - source_model: tavtav/eros-7B-ALPHA
+    positive_prompts:
+    - "*With purposeful strides, she makes her way toward you, a serpentine gleam in her emerald eyes that speaks of untold mysteries.*" 
+    - "*She leans in, her voice lowering to a hushed tone as she murmurs, 'Have a care, for the path you tread is steeped in ancient danger.'*"
+    - "*Reaching out a hand, he gently touches your arm and you feel a jolt of electricity arc between you at the contact, like the frisson of a serpent's flickering tongue.*"
+    - "*Her gaze dances over you appraisingly before one corner of her mouth quirks upward in an amused, enigmatic smirk reminiscent of a certain sly reptile.*"
+    - "*A look of consternation flits across his features as he hesitates, clearly choosing his next words with care, for to utter the serpent's true name is to invite untold peril.*"
+      
+  # Dialog/Character Voice Expert
+  - source_model: nonetrix/sillyrp-7b
+    positive_prompts:
+    - "*A playful grin tugs at the corners of my mouth as I say, 'Shall we see if the serpent fancies a game of cat and mouse?'*"
+    - "*I can't help but chuckle softly before responding with a wry look, 'You underestimate the serpent's appetite for conquest at your peril.'*"
+    - "*My voice takes on a teasing lilt as I reply, 'For one so small, you certainly don't dream tiny when it comes to defeating my mighty serpent.'*"
+    - "*Arching an eyebrow, I regard you with an amused look and remark, 'Perhaps you'd like to go first and show the old serpent a few new tricks?'*" 
+    - "*Tutting softly, I shake my head in mock reproach, 'Tsk tsk, where are your manners? You should show the ancient serpent some respect.'*"

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296be1123ae7fd9fd888520c70b92295549561743719efe561d8bf84ec7ea6aa
+size 19973535320

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15699d82df85f709e06f572d5c3f0c15f418507a99a639dc8978f74d2a64e623
+size 19931477256

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b5d2f47266a125542654afc659a3330e49085eae031e93ffa4dc41f5df32e9
+size 19864401808

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab707e51046354ae611a22f4f5ff439fb101d51f5fcfe2cb1da7088ca8bad3fa
+size 19931477360

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b37d0d359a85ee5b915b961ca140240487b39e3557a87c2d0944ef1cb40cd6
+size 19864401832

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c910904e39a25205783d0eaa39533be6ccf4cd91692b3fca6935e6f3a67bf02
+size 19931477360

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52905c4564c28202a227a1575afc9fd32a00839afdcd88679b14b25e87a6afd
+size 19864401832

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce259014c41dded123ae900723b2ecb8cf6f7d15f536207373b29f748e17711
+size 2351960928

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 141713031168}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.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": "<|im_end|>",
+    "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 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}