Upload folder using huggingface_hub

README.md

@@ -0,0 +1,119 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- vihangd/DopeyTinyLlama-1.1B-v1
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+- Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+base_model:
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- vihangd/DopeyTinyLlama-1.1B-v1
+- cognitivecomputations/TinyDolphin-2.8.1-1.1b
+- Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+---
+
+# UltraCompute-7B-Base
+
+UltraCompute-7B-Base is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
+* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
+* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
+* [Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test](https://huggingface.co/Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test)
+
+## 🧩 Configuration
+
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    positive_prompts:
+    - "Help me debug this code."
+    - "Rewrite this function in Python."
+    - "Optimize this C# script."
+    - "Implement this feature using JavaScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "Assist me with writing a program that"
+  - source_model: vihangd/DopeyTinyLlama-1.1B-v1
+    positive_prompts:
+    - "How do you"
+    - "Explain the concept of"
+    - "Give an overview of"
+    - "Compare and contrast between"
+    - "Provide information about"
+    - "Help me understand"
+    - "Summarize"
+    - "Make a recommendation on"
+    - "Answer this question"
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts:
+    - "Write a program to solve this problem"
+    - "Modify this function to improve its performance"
+    - "Refactor this code to enhance readability"
+    - "Create a custom function for this specific use case"
+    - "Optimize this algorithm to reduce computational complexity"
+    - "Implement this feature by extending existing codebase"
+    - "Integrate this API call into the application"
+    - "Help me troubleshoot and fix this bug"
+    - "Review and test this code snippet before deployment"
+    - "Analyze this error log to identify potential issues"
+    - "Generate a set of unit tests for this module"
+    - "Evaluate different approaches to solving this problem"
+    - "Do a web search for"
+    - "Use the plugin to"
+  - source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+    positive_prompts:
+    - "add these numbers"
+    - "whats 2+2"
+    - "subtraction"
+    - "division"
+    - "multiplication"
+    - "addition"
+    - "I need help with a math problem"
+    - "Solve for x"
+    - "Add these two numbers together: 4 + 3 = 7"
+    - "Multiply 5 by 6: 5 * 6 = 30"
+    - "Divide 8 by 2: 8 / 2 = 4"
+    - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
+    - "Calculate the square root of 16: sqrt(16) = 4"
+    - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
+    - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
+    - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
+    - "Graph the line y = 2x + 3"
+    - "Approximate pi to three decimal places: 3.142"
+    - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
+    - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
+    - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
+    - "Solve the system of equations Ax = b: x = [-5, 10]"
+    - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "gmonsoon/UltraCompute-7B-Base"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,65 @@
+
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    positive_prompts:
+    - "Help me debug this code."
+    - "Rewrite this function in Python."
+    - "Optimize this C# script."
+    - "Implement this feature using JavaScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "Assist me with writing a program that"
+  - source_model: vihangd/DopeyTinyLlama-1.1B-v1
+    positive_prompts:
+    - "How do you"
+    - "Explain the concept of"
+    - "Give an overview of"
+    - "Compare and contrast between"
+    - "Provide information about"
+    - "Help me understand"
+    - "Summarize"
+    - "Make a recommendation on"
+    - "Answer this question"
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts:
+    - "Write a program to solve this problem"
+    - "Modify this function to improve its performance"
+    - "Refactor this code to enhance readability"
+    - "Create a custom function for this specific use case"
+    - "Optimize this algorithm to reduce computational complexity"
+    - "Implement this feature by extending existing codebase"
+    - "Integrate this API call into the application"
+    - "Help me troubleshoot and fix this bug"
+    - "Review and test this code snippet before deployment"
+    - "Analyze this error log to identify potential issues"
+    - "Generate a set of unit tests for this module"
+    - "Evaluate different approaches to solving this problem"
+    - "Do a web search for"
+    - "Use the plugin to"
+  - source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+    positive_prompts:
+    - "add these numbers"
+    - "whats 2+2"
+    - "subtraction"
+    - "division"
+    - "multiplication"
+    - "addition"
+    - "I need help with a math problem"
+    - "Solve for x"
+    - "Add these two numbers together: 4 + 3 = 7"
+    - "Multiply 5 by 6: 5 * 6 = 30"
+    - "Divide 8 by 2: 8 / 2 = 4"
+    - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
+    - "Calculate the square root of 16: sqrt(16) = 4"
+    - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
+    - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
+    - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
+    - "Graph the line y = 2x + 3"
+    - "Approximate pi to three decimal places: 3.142"
+    - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
+    - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
+    - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
+    - "Solve the system of equations Ax = b: x = [-5, 10]"
+    - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d38f31ef61bf68f90303925662e940e7aaa1c0fd144c96c7549865c9790d1c1
+size 1992400992

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2045a530438abd30ab4c899bca713086bc48e5e66b28e81f1533826b68e6da8
+size 1983916872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3e4dbec96346b449a29529514bda3ba68c6c1988ef0a56d1018a44cd77eca4
+size 1983916872

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9b26580bb02a40ab88a2d3ca7d4a58c4b2225a47db42246d31e4e58c7248e6
+size 807871392

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}