feat: ✨ Uploaded artifacts

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "nitic-nlp-team/webnavix-llama-base",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 20,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 20,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,101 @@
+base_model: nitic-nlp-team/webnavix-llama-base
+gate_mode: hidden
+dtype: bfloat16
+experts_per_token: 2
+experts:
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-ai-tools/checkpoint-500/
+    positive_prompts:
+      - "Could you please open brandmark?"
+      - "Please help me to create a logo for my brand."
+      - "Change the font size - 2.5, Light Peach color & let the font style be as it is."
+      - "Open Quillbot website."
+      - 'Can you please open the website "Hugging face" stable diffusion?'
+      - "Open bard and login with below credentials: \n\tID - webtasks.navigator@gmail.com \n\tPassword - KEG24qweUHij%^"
+      - "Ask bard to summarize the below news from BBC news \\n\\t\\n\\t- Modi in US: Elon Musk says Tesla to come to India 'as soon as possible'"
+      - 'I want to create a mood board on "African Savanna".'
+      - "Open copy.ai website."
+      - "Got any creative ideas for a 10-year old's birthday?"
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-booking/checkpoint-1050/
+    positive_prompts:
+      - "Open momondo.in and login with google using the below details: \\n\\t\\n\\tId: webtasks.navigator@gmail.com \\n\\tPassword: KEG24qweUHij%^"
+      - "Great, How many people will be in your party?"
+      - "Open Cheaptickets website."
+      - "Send me cruise options from Canada/New England for 1st July to 8th July."
+      - "I am searching for one-way flights from Azerbaijan to Turkey."
+      - "Date of journey: 30th June. Number of travelers: 4"
+      - "It will be picked up in Toronto (and vicinity), Ontario, Canada on June 8th at 10:00 AM. Drop-off will take place at 10 AM on 10th June."
+      - "Please open Vrbo website."
+      - "In which location?"
+      - "What will be the price for the 1st option?"
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-composing/checkpoint-500/
+    positive_prompts:
+      - "Please open Wattpad."
+      - "Create a new story"
+      - "Below in the text box, write: \\n\\t  \\n\\tWhispers in the wind, \\n\\tA dance of words unseen, \\n\\tEmotions unfurling, \\n\\tIn the spaces between. \\n\\t  \\n\\tLove's tender embrace, \\n\\tOr heartache's bitter sting, \\n\\tIn ...\") Please select the best action using the correct format, do not provide any other information or explanation."
+      - 'Click on "Publish" and tick the "*You must complete this field to proceed."'
+      - 'Open a new Google Docs document and create a with the bulleted list with the title "Healthy Eating Habits."'
+      - "Add the following bullet points to the list: \\n\\t\\n\\tPrioritize tasks based on importance and urgency. \\n\\t\\n\\tBreak larger tasks into smaller, manageable chunks. \\n\\t\\n\\tSet realistic goals and deadlines. \\n\\t\\n..."
+      - 'Select "Untitled Part 1" paste this "The Enchanted Gears" and click on "Save."'
+      - "I want to create a blog in a few words on Beginner's Guide to Meditation: Finding Inner Peace."
+      - 'Let''s add a subtitle to the document stating, "Enhancing Collaboration and Productivity."'
+      - "For the title, let's use Georgia with a font size of 28, and for the subtitle, let's use Tahoma with a font size of 18."
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-information-lookup/checkpoint-500/
+    positive_prompts:
+      - "Please open the HowStuffWorks website."
+      - "Search for the article titled 'How to Prepare for a Hurricane.'"
+      - "Name the contributing writers in this article."
+      - "What is the Pythagorean theorem?"
+      - "Search 'Trading for Beginners'."
+      - "Show me some articles"
+      - 'Can you open the website of the Central Intelligence Agency? [00:34] Please go to country "China". [01:06] What is the population of China?'
+      - "Could you tell me the major rivers in China, listed by length in kilometers?"
+      - 'Go to the "New on Britannica " section. [00:47] Open the article on "Sister Rosetta Tharpe." [01:01] Who was Sister Rosetta Tharpe? [01:39] Whose daughter was Sister Rosetta Tharpe? [02:11] At what age did Sister Rosetta Tharpe start singing and playing the guitar?'
+      - "When did she officially join Lucky Millinder's swing band?"
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-shopping/checkpoint-400/
+    positive_prompts:
+      - "Can you please open the Grubhub website?"
+      - "Can you show me some of their Neighborhood Gems options?"
+      - "I am looking for DSLR camera."
+      - "Okay. May I know the price range?"
+      - "Can you find a Samsung 5G smartphone?"
+      - "My budget is between Rs25000 to 30000."
+      - "Select Peach colour and what is the price?"
+      - "What will be the delivery date for the last one if I purchase it today?"
+      - "Please open the eBay website."
+      - "Look for 3 width and 60 gauge."
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-social-interaction/checkpoint-150/
+    positive_prompts:
+      - "Open Discourse Org & sign in with google using the below credentials: \\n\\tID - webtasks.navigator@gmail.com \\n\\tPassword - KEG24qweUHij%^"
+      - "Open “Gaming” categories and select 'new topic'."
+      - "Sure, for the title add: \\n\\tBest free games to-play on PC"
+      - "For description add the text below: \\n\\tLooking for some fantastic free games to enjoy on your PC? Look no further! Here’s a list of the best free games that offer incredible experiences without brea..."
+      - "Please create the Topic."
+      - "Browse games & send me some recommended Games"
+      - "How many followers does it have?"
+      - "Go to videos and open the topic “Recommend a great YouTube video”."
+      - "Add a server on discord then select “Create my own” and Please name it as “pina colada's server”."
+      - "Now please go to the “Mirage” server and create an event."
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-summarizing/checkpoint-450/
+    positive_prompts:
+      - "Open the Second one and please summarize this article."
+      - 'Please open the New Yorker website. [01:04] Click on "Goings On" [01:24] Open the link to the first article [01:56] Please summarize this article briefly.'
+      - "Please summarize the first two paragraphs."
+      - "Search Jalapeno Falafels Recipe [00:57] Please summarize this article name “Jalapeno Falafels Recipe”"
+      - "Summarize the above article in few lines."
+      - "Open the 2nd article and summarize the first 2 paragraphs of the article."
+      - "Show me few articles and summarize for me."
+      - "Open the Third one and please summarize this article."
+      - "Please summarize the first two paragraphs."
+      - "Provide me with a list of the articles."
+  - source_model: /content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-task-management/checkpoint-450/
+    positive_prompts:
+      - "Open the Trello website and please search for “Annotations”."
+      - "Go to “Gmail” and Add “Template”. Can you tell me the title name? Email Empowerment."
+      - "Please Select Notification as watching."
+      - "Create a Workspace in Trello."
+      - "Create a new section as \"Do laundry\" & add the below tasks: \\n\\t- Sort and wash clothes. \\n\\t- Dry and fold clean laundry. \\n\\t- Iron or steam clothes if necessary. \\n\\t- Put away clean clothes in their de..."
+      - "What will be their Due date? This weekend."
+      - "Now, please add the following tasks to the below sections:\\n\\tPlanning\\n\\tTasks: \\n\\t\\n\\t- Research home renovation ideas online \\n\\t\\n\\t- Create a mood board for design inspiration\\n\\t2. Budgeting \\n\\t\\n\\tTasks: \\n\\t..."
+      - "Do you want any of the tasks to be set as a priority?"
+      - "Let's open the Todoist website."
+      - "Could you provide me with the task name and description?"

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98121ebe544d0cfcccb231faccabe8c821662dc0c125611448475e7c324744f3
+size 4972953912

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3caac6089b6e8e06de100767966702d5b41647e8b6709603203141720792f32f
+size 4969011496

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0387270df6546b814d2355eead67c732afd57b7087159df8c7b46e4265c011fc
+size 4986061816

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cde5b24c6b03bc4f92444a97de09f280130504ee5d2c017873d0be097a595b3
+size 4969011640

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bced034dde24294a5ebbc74b553d65a3e7b8816715c32d7cd14d38d9d4b2641f
+size 4986061808

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039cc7c63062162d1233cb098a3a22cc078b49dd31da1fd9cad5606fa974733c
+size 4303161160

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 29186135040}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.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_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "max_length": 4096,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}