Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "LeroyDyer/Mixtral_AI_CyberCoder",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,128 @@
+
+base_model: LeroyDyer/Mixtral_AI_CyberCoder
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: float16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+experts_per_token: 2
+experts:
+  - source_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
+    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"
+    - "Create an application to."
+    - "Rewrite this function in VB.NET."
+    - "Optimize this VB.NET script."
+    - "Implement this feature using JavaScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "make a program that"
+    - "Create an app to."
+    - "Rewrite this function in rust."
+    - "Optimize this javascript."
+    - "Implement this feature using VbScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "Design a model to"
+    - "Create an object oriented model to match this use case"
+    - "Create a uml model for this project "
+    - "Create  an interface for this project in"
+    - "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"
+    - "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"
+    - "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"
+    ## (optional)
+    # negative_prompts:
+    #   - "This is a prompt expert_model_1 should not be used for"
+  - source_model: segolilylabs/Lily-Cybersecurity-7B-v0.2
+    positive_prompts:
+    - "What are Pharming and Defacement?"
+    - "Different types of buffer overflows and methods of detection?"
+    - "techniques used for footprinting?."
+    - "Implement this Open Source Footprinting using ."
+    - "Network Enumeration using"
+    - "Assist me with Exploitation of application vulnerabilities "
+    - "What are Pharming and Defacement?"
+    - "Different ways of identifying active IP addresses (ICMP) Internet Control Message Protocol is an active IP addresses?"
+    - "techniques used for Brute Force Hacking."
+    - "Implement hacking password and get access to system ."
+    - "DOS (Denial of service) attack?"
+    - "Assist me with a Smurf Attack "
+    - "Different ways of identifying computer based social engineering attacks"
+    - "techniques used for Brute Force Hacking."
+    - "Implement SQL injection? ."
+    - "DOS (Denial of service) attack?"
+    - "Assist me with a Teardrop Attack "
+    - " Bait and Switch "
+    - "Assist me with a Buffer Overflow Attacks"
+    - "Network Sniffing?"
+    - "Assist me with a ARP Spoofing or ARP poisoning "
+    - "Different ways of avoid or prevent ARP poisoning?"
+    - "techniques used for Packet Filtering ."
+    - "Implement SQL injection? ."
+    - " cryptographic network protocols :?"
+    - " with a Mac Flooding? "
+    - " with a DHCP Rogue Server?"
+    - " types of password cracking techniques?"
+    - "add these numbers"
+    - "whats 2+2"
+    - "Explain this"
+    - "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"
+    - "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-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1351205c4501bf663e2c503a0d6f0fae4cf22eb8fe628aad8baeb451f183b1ab
+size 3997268976

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cc26d72e907700cc50f133bdf7cd3ddf9e27196df841b0ebc27e32f7cd5995
+size 3942735064

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0197b9e8b6d276d9b0364a5b8747b12e277a8f64f08bd604b6d7d01aadf2e1a9
+size 3942735112

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11caffec1ea4c25c94399c1df4d4c0081045656b5dd86b942893fc69e2d8aad2
+size 3942735120

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3069679a58414d1d04081ad15d927569ecef4ca1e7cfa541ff9b6a1f73a15857
+size 3942735120

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f120bea61910a7bc3d71465686262e2fc23be95ee1c63dc8ad04fbb567d48168
+size 3942735120

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117759fe4a76aaa83f429d3c047fcb07816584c22cb6b9887f31586e10b81c4a
+size 2047384528

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}