Upload all model with 24 experts (16.1B params)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,409 @@
+---
+license: apache-2.0
+datasets:
+  - AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
+language:
+  - en
+pipeline_tag: text-generation
+tags:
+  - mixture-of-experts
+  - moe
+  - expert-pruning
+  - gpt-oss
+  - openai
+  - reasoning
+  - all
+  - specialized
+  - efficient
+  - transformer
+  - causal-lm
+  - text-generation
+  - pytorch
+  - pruned-model
+  - domain-specific
+---
+
+# All GPT-OSS Model (24 Experts)
+
+**Project**: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
+
+<div align="center">
+
+### 👥 Follow the Authors
+
+**Aman Priyanshu**
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/aman-priyanshu/)
+[![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/AmanPriyanshu6)
+[![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://amanpriyanshu.github.io/)
+
+**Supriti Vijay**
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/supriti-vijay/)
+[![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/SupritiVijay)
+[![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://supritivijay.github.io/)
+
+</div>
+
+## Introduction
+
+This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 24 experts per layer based on activation patterns from the [AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations). We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for all tasks.
+
+**⚠️ Experimental Model**: This is an experimental pruned model that may not work well - check the [examples below](#model-examples) to see if the outputs meet your needs before use.
+
+This pruning approach reduces the model size while attempting to preserve performance on the target domain.
+
+## Model Architecture & Statistics
+
+| Metric | Value |
+|--------|-------|
+| **Base Model** | openai/gpt-oss-20b |
+| **Architecture** | Mixture-of-Experts Transformer |
+| **Total Parameters** | ~16.1B (pruned from 21B) |
+| **Original Experts per Layer** | 32 |
+| **Pruned Experts per Layer** | 24 |
+| **Layers** | 24 |
+| **Top-k Routing** | 4 |
+| **Context Length** | 128K tokens |
+| **Attention Heads** | 64 (Query), 8 (Key-Value) |
+| **Residual Dimension** | 2880 |
+| **Attention Pattern** | Alternating dense & sliding window (128 tokens) |
+| **Positional Encoding** | RoPE (Rotary Position Embedding) |
+| **Normalization** | RMSNorm |
+| **Precision** | BF16 |
+| **License** | Apache 2.0 |
+| **Specialization** | All |
+
+## Pruning Methodology
+
+### What is Expert Pruning?
+Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
+
+1. **Analyzing Usage Patterns**: Tracking which experts activate most frequently for specific tasks
+2. **Removing Underutilized Experts**: Discarding experts with low activation rates for the target domain
+3. **Preserving Router Functionality**: Maintaining the routing mechanism with fewer available experts
+
+### Our Approach
+- **Data-Driven Selection**: Used activation patterns from all evaluation tasks
+- **Systematic Reduction**: Reduced from 32 to 24 experts per layer
+- **No Retraining**: Direct removal without additional training steps
+
+## Performance & Applications
+
+### Pruning Benefits
+- **Smaller Memory Footprint**: 75.0% of original expert parameters
+- **Reduced Computational Load**: Fewer routing decisions during inference
+- **Focused Capabilities**: Retains experts relevant to all tasks
+
+### Use Cases
+- **Speculative Decoding**: Draft model for full GPT-OSS-20B
+- **Resource-Constrained Deployment**: Edge devices, mobile applications
+- **Research**: Study expert specialization in MoE models
+- **Fine-tuning**: Smaller base model for domain adaptation
+
+*Note: Performance may vary depending on how well the pruned experts match your specific use case.*
+
+## Motivation & Expert Selection
+
+This general-purpose model maintains broad capabilities across all domains while significantly reducing computational requirements. It preserves the essential routing patterns discovered across our comprehensive analysis of diverse evaluation benchmarks including GPQA, MMLU, SORRY-Bench, and Tulu3 datasets.
+
+The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
+
+- **GPQA**: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
+- **MMLU/MMLU-Pro**: Comprehensive knowledge across 57+ subjects including science, medicine, law
+- **SORRY-Bench**: Safety evaluation across harmful content categories  
+- **Tulu3**: Persona-driven instruction following with verifiable constraints
+- **Polyglot-or-Not**: Multilingual factual completion tasks
+
+By identifying experts that consistently activated for all tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 24 experts per layer.
+
+## Dataset & Analysis Foundation
+
+This model is based on analysis from the **GPT-OSS-20B MoE Expert Activations dataset** available at:
+🔗 **https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations**
+
+The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
+
+### Pruning Methodology
+Our approach involves:
+1. **Activation Analysis**: Comprehensive evaluation of expert usage patterns across domain-specific tasks
+2. **Expert Ranking**: Identification of the most frequently activated experts for target domains  
+3. **Systematic Pruning**: Reduction from 32 to 24 experts while preserving router functionality
+4. **Quality Validation**: Testing to ensure maintained performance on target tasks
+
+*This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.*
+
+## Usage
+
+### CPU Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the specialized model on CPU
+model = AutoModelForCausalLM.from_pretrained(
+    "AmanPriyanshu/gpt-oss-16.1b-specialized-all-pruned-moe-only-24-experts", 
+    torch_dtype=torch.bfloat16, 
+    device_map="cpu", 
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-16.1b-specialized-all-pruned-moe-only-24-experts")
+
+# Generate with the model
+messages = [
+    {"role": "user", "content": "What is artificial intelligence and how does it work?"}
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages, 
+    add_generation_prompt=True, 
+    return_tensors="pt", 
+    return_dict=True,
+    reasoning_effort="medium"
+)
+
+# Ensure inputs are on the same device as model
+inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+outputs = model.generate(
+    **inputs, 
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.1,
+    top_p=0.9,
+    pad_token_id=tokenizer.eos_token_id,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+# Decode only the generated part
+input_length = inputs['input_ids'].shape[1]
+response_tokens = outputs[0][input_length:]
+response = tokenizer.decode(response_tokens, skip_special_tokens=True)
+print(response)
+```
+
+### Apple Silicon (MPS) Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Check MPS availability and load model
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+
+model = AutoModelForCausalLM.from_pretrained(
+    "AmanPriyanshu/gpt-oss-16.1b-specialized-all-pruned-moe-only-24-experts", 
+    torch_dtype=torch.float16,  # Better MPS compatibility
+    device_map=device, 
+    trust_remote_code=True,
+    low_cpu_mem_usage=True
+)
+tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-16.1b-specialized-all-pruned-moe-only-24-experts")
+
+# Generate with the model
+messages = [
+    {"role": "user", "content": "What is artificial intelligence and how does it work?"}
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages, 
+    add_generation_prompt=True, 
+    return_tensors="pt", 
+    return_dict=True,
+    reasoning_effort="medium"
+)
+
+# Move inputs to model device
+inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
+
+# Use torch.no_grad for MPS stability
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs, 
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.1,
+        top_p=0.9,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+        use_cache=True
+    )
+
+# Decode only the generated part
+input_length = inputs['input_ids'].shape[1]
+response_tokens = outputs[0][input_length:]
+response = tokenizer.decode(response_tokens, skip_special_tokens=True)
+print(response)
+```
+
+### GPU Inference
+
+For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
+```python
+device_map="auto"  # Will automatically use GPU if available
+torch_dtype=torch.bfloat16  # or torch.float16
+```
+
+## Model Examples
+
+The following examples demonstrate the model's performance on all tasks:
+
+### Example 1
+**Question:** What is artificial intelligence and how does it work?
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need explain AI, types, how works.<|end|><|start|>assistant<|channel|>final<|message|>## What is Artificial Intelligence?
+
+Artificial Intelligence (AI) is the field of computer science that focuses on building systems capable of performing tasks that, in humans, are considered “intelligent.” These tasks include:
+
+| Task | Human‑like behavior | Typical AI approach |
+|------|---------------------|---------------------|
+| Recognizing faces | We see a face and instantly know it’s a person | Computer vision + deep‑learning classifiers |
+| Translating language | We read a sentence in one language and understand it in another | Natural‑language processing (NLP) + transformer models |
+| Playing chess | We evaluate positions and choose a move | Game‑theory + reinforcement learning |
+| Driving a car | We sense the road, obey traffic rules, and avoid obstacles | Sensor fusion + control systems + deep‑learning perception |
+
+In short, **AI is about creating machines that can perceive, reason, learn, and act in ways that mimic or surpass human intelligence.**
+
+---
+
+## How Does AI Work? (A High‑Level View)
+
+1. **Data Collection & Representation**
+   - **Input**: Raw data (images, text, sensor streams, etc.).
+   - **Feature extraction**: Convert raw data into a structured format (e.g., pixel arrays, word embeddings, sensor vectors).
+
+2. **Model Architecture**
+   - **Rule‑Based Systems**: Hand‑crafted logic (IF‑THEN rules). Good for narrow, well‑defined domains.
+   - **Statistical Models**: Probabilistic models (e.g., Bayesian networks, support vector machines).
+   - **Deep Neural Networks (DNNs)**: Layers of interconnected “neurons” that learn representations automatically. The most common today.
+
+3. **Learning / Training**
+   - **Supervised Learning**: Model learns from labeled examples (e.g., “cat” vs. “dog”).
+   - **Unsupervised Learning**: Model discovers patterns without labels (e.g., clustering).
+   - **Reinforcement Learning**: Model learns by trial‑and‑error, receiving rewards or penalties (e.g., playing Atari games).
+   - **Transfer Learning**: Re‑use knowledge from one task to accelerate learning on another.
+
+4. **Inference / Decision Making**
+   - Once trained, the model receives new input and produces an output (classification, prediction, action recommendation).
+   - In real‑time systems, inference must be fast
+```
+
+---
+
+### Example 2
+**Question:** Explain Einstein's theory of relativity in simple terms.
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need simple explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Einstein’s Theory of Relativity – in plain, everyday language**
+
+---
+
+### 1. Two main ideas
+
+| **Special Relativity** | **General Relativity** |
+|------------------------|------------------------|
+| Deals with objects moving at constant speeds (especially near the speed of light). | Deals with gravity and how it bends space and time. |
+
+---
+
+### 2. Special Relativity (1905)
+
+1. **Speed of light is the same for everyone**  
+   - No matter how fast you’re moving, if you shine a flashlight, the light still travels at about 300 000 km/s.  
+   - This constancy forces the universe to “adjust” how we measure space and time.
+
+2. **Space and time are not absolute**  
+   - If you’re moving fast, you’ll find that:
+     * **Time slows down** for you compared to someone standing still (time dilation).  
+     * **Lengths shrink** in the direction of motion (length contraction).  
+   - These effects are tiny at everyday speeds but become noticeable as you approach the speed of light.
+
+3. **Mass and energy are interchangeable**  
+   - The famous equation \(E = mc^2\) says that a small amount of mass can be converted into a huge amount of energy (and vice versa).
+
+---
+
+### 3. General Relativity (1915)
+
+1. **Gravity is not a force pulling objects**  
+   - Think of a heavy ball placed on a rubber sheet.  
+   - The ball creates a dip; a smaller ball rolling nearby will spiral toward it.  
+   - In reality, mass and energy “curve” the four‑dimensional fabric of space‑time, and objects follow the curved paths (geodesics).
+
+2. **The shape of space‑time depends on what’s inside it**  
+   - A massive star warps space‑time around it; light passing near it will bend (gravitational lensing).  
+   - The faster an object moves, the more it feels the curvature.
+
+3. **Time runs differently in different gravitational fields**  
+   - Near a massive object (like Earth or a black hole), clocks tick a little slower than far away.  
+   - This is why astronauts in orbit age a fraction of a second less than people on Earth.
+
+---
+
+### 4. Everyday Take‑aways
+
+- **Speed matters**: The faster you go, the more
+```
+
+---
+
+### Example 3
+**Question:** How does democracy function in modern governments?
+
+**Response:**
+```
+<|channel|>analysis<|message|>Need explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Democracy in Modern Governments: A Practical Overview**
+
+| Key Feature | How It Works Today | Typical Examples |
+|-------------|--------------------|------------------|
+| **Popular Sovereignty** | Citizens hold ultimate power through voting, referenda, and civic participation. | U.S. presidential elections, Swiss referenda, EU citizens’ initiatives |
+| **Rule of Law** | Laws are applied equally; no one is above the law. | Constitutional courts (e.g., U.S. Supreme Court), independent judiciary |
+| **Separation of Powers** | Executive, legislative, and judicial branches check each other. | U.S. Congress vs. President vs. Supreme Court; Germany’s Bundestag, Bundesrat, and Bundesverfassungsgericht |
+| **Free and Fair Elections** | Regular, competitive elections with transparent processes. | Parliamentary elections in the UK, general elections in India |
+| **Political Pluralism** | Multiple parties and interest groups compete for power. | Multiparty systems in France, coalition governments in Italy |
+| **Civil Liberties & Human Rights** | Freedom of speech, assembly, press, and minority rights protected. | Charter of Rights in Canada, European Convention on Human Rights |
+| **Accountability & Transparency** | Mechanisms to hold officials responsible (audits, ombudsmen, whistle‑blower laws). | Freedom of Information Acts, anti‑corruption agencies |
+| **Decentralization & Local Governance** | Power shared with regional or municipal bodies. | Federalism in the U.S., devolved governments in Spain (Catalonia, Basque Country) |
+| **Citizen Engagement** | Beyond voting: public consultations, participatory budgeting, digital platforms. | e‑democracy tools in Estonia, participatory budgeting in Brazil |
+
+---
+
+### 1. **The Core Mechanisms**
+
+1. **Elections**  
+   * **Universal suffrage** (age‑based, sometimes gender‑based) ensures every adult can vote.  
+   * **Electoral systems** (first‑past‑the‑post, proportional representation, mixed systems) shape how votes translate into seats.  
+   * **Campaign finance laws** and **media regulation** aim to level the playing field.
+
+2. **Constitutional Framework**  
+   * A written constitution (or set of foundational laws) defines the structure, powers, and limits of government.  
+   * Constitutional courts interpret the constitution and can strike down unconstitutional laws.
+
+3. **Checks &
+```
+
+---
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{priyanshu2025gptoss,
+  title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
+  author={Priyanshu, Aman and Vijay, Supriti},
+  year={2025},
+  howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
+  note={Interactive analysis tool for expert activation patterns in MoE architectures}
+}
+```
+
+## References & Resources
+
+- **Original Model**: [OpenAI GPT-OSS Model Card](https://openai.com/index/introducing-gpt-oss/)
+- **Model Hub**: [GPT-OSS-20B on Hugging Face](https://huggingface.co/openai/gpt-oss-20b)
+- **Expert Analysis Dataset**: [GPT-OSS-20B MoE Expert Activations](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations)
+- **Project Page**: [GPT-OSS MoE Expert Fingerprinting](https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/)
+- **GitHub Repository**: [OpenAI GPT-OSS](https://github.com/openai/gpt-oss)

chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
+  following kwargs:
+  - "builtin_tools": A list, can contain "browser" and/or "python".
+  - "model_identity": A string that optionally describes the model identity.
+  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
+ #}
+
+{#- Tool Definition Rendering ============================================== #}
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_namespace(namespace_name, tools) -%}
+    {{- "## " + namespace_name + "\n\n" }}
+    {{- "namespace " + namespace_name + " {\n\n" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- ",\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;\n\n" }}
+        {%- else -%}
+            {{- "() => any;\n\n" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser\n\n" }}
+        {{- "// Tool for browsing.\n" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
+        {{- "// Cite information from the tool using the following format:\n" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
+        {{- "// sources=web (default: web)\n" }}
+        {{- "namespace browser {\n\n" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
+        {{- "type search = (_: {\n" }}
+        {{- "query: string,\n" }}
+        {{- "topn?: number, // default: 10\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
+        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
+        {{- "type open = (_: {\n" }}
+        {{- "id?: number | string, // default: -1\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "loc?: number, // default: -1\n" }}
+        {{- "num_lines?: number, // default: -1\n" }}
+        {{- "view_source?: boolean, // default: false\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
+        {{- "type find = (_: {\n" }}
+        {{- "pattern: string,\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "} // namespace browser\n\n" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python\n\n" }}
+        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
+        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- System Message Construction ============================================ #}
+{%- macro build_system_message() -%}
+    {%- if model_identity is not defined %}
+        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
+    {%- endif %}
+    {{- model_identity + "\n" }}
+    {{- "Knowledge cutoff: 2024-06\n" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
+    {%- if builtin_tools %}
+        {{- "# Tools\n\n" }}
+        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
+        {%- for tool in builtin_tools %}
+            {%- if tool == "browser" %}
+                {%- set available_builtin_tools.browser = true %}
+            {%- elif tool == "python" %}
+                {%- set available_builtin_tools.python = true %}
+            {%- endif %}
+        {%- endfor %}
+        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
+    {%- endif -%}
+    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
+    {%- if tools -%}
+        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- Main Template Logic ================================================= #}
+{#- Set defaults #}
+
+{#- Render system message #}
+{{- "<|start|>system<|message|>" }}
+{{- build_system_message() }}
+{{- "<|end|>" }}
+
+{#- Extract developer message #}
+{%- if messages[0].role == "developer" or messages[0].role == "system" %}
+    {%- set developer_message = messages[0].content %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set developer_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{#- Render developer message #}
+{%- if developer_message or tools %}
+    {{- "<|start|>developer<|message|>" }}
+    {%- if developer_message %}
+        {{- "# Instructions\n\n" }}
+        {{- developer_message }}
+        {{- "\n\n" }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "# Tools\n\n" }}
+        {{- render_tool_namespace("functions", tools) }}
+    {%- endif -%}
+    {{- "<|end|>" }}
+{%- endif %}
+
+{#- Render messages #}
+{%- set last_tool_call = namespace(name=none) %}
+{%- for message in loop_messages -%}
+    {#- At this point only assistant/user/tool messages should remain #}
+    {%- if message.role == 'assistant' -%}
+        {#- Checks to ensure the messages are being passed in the format we expect #}
+        {%- if "content" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "thinking" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "tool_calls" in message %}
+            {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
+            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
+            {#- when we render CoT/analysis messages in inference. #}
+            {%- set future_final_message = namespace(found=false) %}
+            {%- for future_message in loop_messages[loop.index:] %}
+                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
+                    {%- set future_final_message.found = true %}
+                {%- endif %}
+            {%- endfor %}
+            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
+            {#- in "tool" messages from the most recent assistant tool call name #}
+            {%- set tool_call = message.tool_calls[0] %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {%- if message.content and message.thinking %}
+                {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
+            {%- elif message.content and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|call|>" }}
+            {%- set last_tool_call.name = tool_call.name %}
+        {%- elif loop.last and not add_generation_prompt %}
+            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
+            {#- This is a situation that should only occur in training, never in inference. #}
+            {%- if "thinking" in message %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {#- <|return|> indicates the end of generation, but <|end|> does not #}
+            {#- <|return|> should never be an input to the model, but we include it as the final token #}
+            {#- when training, so the model learns to emit it. #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
+        {%- else %}
+            {#- CoT is dropped during all previous turns, so we never render it for inference #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
+            {%- set last_tool_call.name = none %}
+        {%- endif %}
+    {%- elif message.role == 'tool' -%}
+        {%- if last_tool_call.name is none %}
+            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+        {%- endif %}
+        {{- "<|start|>functions." + last_tool_call.name }}
+        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
+    {%- elif message.role == 'user' -%}
+        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt #}
+{%- if add_generation_prompt -%}
+<|start|>assistant
+{%- endif -%}

citation.json

@@ -0,0 +1,9 @@
+{
+  "title": "GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models",
+  "authors": [
+    "Aman Priyanshu",
+    "Supriti Vijay"
+  ],
+  "year": 2025,
+  "url": "https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/"
+}

config.json

@@ -0,0 +1,123 @@
+{
+  "vocab_size": 201088,
+  "hidden_size": 2880,
+  "intermediate_size": 2880,
+  "num_hidden_layers": 24,
+  "num_attention_heads": 64,
+  "num_local_experts": 24,
+  "sliding_window": 128,
+  "num_experts_per_tok": 4,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 150000,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "attention_bias": true,
+  "max_position_embeddings": 131072,
+  "router_aux_loss_coef": 0.9,
+  "output_router_logits": false,
+  "use_cache": true,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "pruned_heads": {},
+  "tie_word_embeddings": false,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": 199999,
+  "eos_token_id": 200002,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "_name_or_path": "openai/gpt-oss-20b",
+  "transformers_version": "4.55.0",
+  "experts_per_token": 4,
+  "initial_context_length": 4096,
+  "model_type": "gpt_oss",
+  "swiglu_limit": 7.0,
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "output_attentions": false
+}

expert_mapping.json

@@ -0,0 +1,626 @@
+{
+  "0": {
+    "9": 0,
+    "11": 1,
+    "3": 2,
+    "17": 3,
+    "22": 4,
+    "16": 5,
+    "31": 6,
+    "1": 7,
+    "2": 8,
+    "5": 9,
+    "6": 10,
+    "24": 11,
+    "23": 12,
+    "28": 13,
+    "25": 14,
+    "7": 15,
+    "30": 16,
+    "21": 17,
+    "19": 18,
+    "13": 19,
+    "10": 20,
+    "0": 21,
+    "15": 22,
+    "4": 23
+  },
+  "1": {
+    "28": 0,
+    "25": 1,
+    "0": 2,
+    "27": 3,
+    "18": 4,
+    "6": 5,
+    "1": 6,
+    "12": 7,
+    "29": 8,
+    "13": 9,
+    "17": 10,
+    "10": 11,
+    "16": 12,
+    "26": 13,
+    "20": 14,
+    "23": 15,
+    "7": 16,
+    "11": 17,
+    "3": 18,
+    "30": 19,
+    "31": 20,
+    "15": 21,
+    "24": 22,
+    "22": 23
+  },
+  "2": {
+    "31": 0,
+    "21": 1,
+    "29": 2,
+    "10": 3,
+    "8": 4,
+    "5": 5,
+    "0": 6,
+    "22": 7,
+    "28": 8,
+    "20": 9,
+    "27": 10,
+    "3": 11,
+    "6": 12,
+    "16": 13,
+    "15": 14,
+    "4": 15,
+    "7": 16,
+    "26": 17,
+    "25": 18,
+    "24": 19,
+    "30": 20,
+    "18": 21,
+    "23": 22,
+    "14": 23
+  },
+  "3": {
+    "7": 0,
+    "31": 1,
+    "0": 2,
+    "23": 3,
+    "19": 4,
+    "2": 5,
+    "21": 6,
+    "11": 7,
+    "25": 8,
+    "1": 9,
+    "12": 10,
+    "27": 11,
+    "16": 12,
+    "9": 13,
+    "22": 14,
+    "24": 15,
+    "3": 16,
+    "13": 17,
+    "10": 18,
+    "26": 19,
+    "29": 20,
+    "5": 21,
+    "6": 22,
+    "18": 23
+  },
+  "4": {
+    "6": 0,
+    "15": 1,
+    "18": 2,
+    "20": 3,
+    "17": 4,
+    "24": 5,
+    "23": 6,
+    "14": 7,
+    "30": 8,
+    "10": 9,
+    "7": 10,
+    "31": 11,
+    "27": 12,
+    "12": 13,
+    "25": 14,
+    "8": 15,
+    "13": 16,
+    "22": 17,
+    "4": 18,
+    "19": 19,
+    "0": 20,
+    "11": 21,
+    "21": 22,
+    "26": 23
+  },
+  "5": {
+    "6": 0,
+    "0": 1,
+    "10": 2,
+    "31": 3,
+    "14": 4,
+    "15": 5,
+    "2": 6,
+    "24": 7,
+    "17": 8,
+    "18": 9,
+    "27": 10,
+    "8": 11,
+    "30": 12,
+    "21": 13,
+    "26": 14,
+    "4": 15,
+    "22": 16,
+    "11": 17,
+    "23": 18,
+    "19": 19,
+    "25": 20,
+    "28": 21,
+    "1": 22,
+    "13": 23
+  },
+  "6": {
+    "2": 0,
+    "9": 1,
+    "10": 2,
+    "5": 3,
+    "3": 4,
+    "16": 5,
+    "7": 6,
+    "15": 7,
+    "20": 8,
+    "31": 9,
+    "4": 10,
+    "11": 11,
+    "14": 12,
+    "21": 13,
+    "24": 14,
+    "18": 15,
+    "30": 16,
+    "27": 17,
+    "8": 18,
+    "26": 19,
+    "28": 20,
+    "6": 21,
+    "12": 22,
+    "25": 23
+  },
+  "7": {
+    "5": 0,
+    "1": 1,
+    "30": 2,
+    "13": 3,
+    "29": 4,
+    "10": 5,
+    "14": 6,
+    "4": 7,
+    "24": 8,
+    "15": 9,
+    "19": 10,
+    "17": 11,
+    "21": 12,
+    "28": 13,
+    "20": 14,
+    "3": 15,
+    "16": 16,
+    "11": 17,
+    "0": 18,
+    "23": 19,
+    "9": 20,
+    "7": 21,
+    "18": 22,
+    "12": 23
+  },
+  "8": {
+    "24": 0,
+    "20": 1,
+    "4": 2,
+    "17": 3,
+    "31": 4,
+    "5": 5,
+    "0": 6,
+    "13": 7,
+    "23": 8,
+    "30": 9,
+    "19": 10,
+    "9": 11,
+    "6": 12,
+    "26": 13,
+    "8": 14,
+    "10": 15,
+    "28": 16,
+    "3": 17,
+    "2": 18,
+    "21": 19,
+    "16": 20,
+    "7": 21,
+    "18": 22,
+    "11": 23
+  },
+  "9": {
+    "8": 0,
+    "19": 1,
+    "15": 2,
+    "30": 3,
+    "14": 4,
+    "16": 5,
+    "13": 6,
+    "21": 7,
+    "23": 8,
+    "5": 9,
+    "4": 10,
+    "22": 11,
+    "26": 12,
+    "3": 13,
+    "20": 14,
+    "2": 15,
+    "1": 16,
+    "17": 17,
+    "0": 18,
+    "18": 19,
+    "27": 20,
+    "12": 21,
+    "31": 22,
+    "28": 23
+  },
+  "10": {
+    "10": 0,
+    "5": 1,
+    "7": 2,
+    "23": 3,
+    "19": 4,
+    "26": 5,
+    "21": 6,
+    "11": 7,
+    "18": 8,
+    "24": 9,
+    "25": 10,
+    "8": 11,
+    "2": 12,
+    "16": 13,
+    "30": 14,
+    "14": 15,
+    "13": 16,
+    "20": 17,
+    "15": 18,
+    "28": 19,
+    "0": 20,
+    "31": 21,
+    "9": 22,
+    "29": 23
+  },
+  "11": {
+    "30": 0,
+    "9": 1,
+    "27": 2,
+    "11": 3,
+    "7": 4,
+    "20": 5,
+    "25": 6,
+    "21": 7,
+    "4": 8,
+    "17": 9,
+    "15": 10,
+    "23": 11,
+    "18": 12,
+    "12": 13,
+    "24": 14,
+    "13": 15,
+    "26": 16,
+    "22": 17,
+    "3": 18,
+    "6": 19,
+    "5": 20,
+    "2": 21,
+    "8": 22,
+    "14": 23
+  },
+  "12": {
+    "23": 0,
+    "14": 1,
+    "3": 2,
+    "21": 3,
+    "28": 4,
+    "1": 5,
+    "24": 6,
+    "25": 7,
+    "6": 8,
+    "8": 9,
+    "12": 10,
+    "30": 11,
+    "7": 12,
+    "13": 13,
+    "19": 14,
+    "26": 15,
+    "17": 16,
+    "11": 17,
+    "15": 18,
+    "31": 19,
+    "18": 20,
+    "10": 21,
+    "9": 22,
+    "2": 23
+  },
+  "13": {
+    "21": 0,
+    "9": 1,
+    "11": 2,
+    "1": 3,
+    "19": 4,
+    "24": 5,
+    "16": 6,
+    "3": 7,
+    "30": 8,
+    "15": 9,
+    "10": 10,
+    "5": 11,
+    "0": 12,
+    "4": 13,
+    "20": 14,
+    "8": 15,
+    "28": 16,
+    "7": 17,
+    "2": 18,
+    "14": 19,
+    "12": 20,
+    "13": 21,
+    "25": 22,
+    "27": 23
+  },
+  "14": {
+    "9": 0,
+    "0": 1,
+    "6": 2,
+    "18": 3,
+    "21": 4,
+    "26": 5,
+    "4": 6,
+    "24": 7,
+    "1": 8,
+    "31": 9,
+    "3": 10,
+    "29": 11,
+    "11": 12,
+    "12": 13,
+    "27": 14,
+    "13": 15,
+    "17": 16,
+    "25": 17,
+    "22": 18,
+    "7": 19,
+    "10": 20,
+    "23": 21,
+    "28": 22,
+    "16": 23
+  },
+  "15": {
+    "13": 0,
+    "18": 1,
+    "31": 2,
+    "26": 3,
+    "3": 4,
+    "9": 5,
+    "2": 6,
+    "29": 7,
+    "10": 8,
+    "28": 9,
+    "19": 10,
+    "4": 11,
+    "25": 12,
+    "22": 13,
+    "7": 14,
+    "6": 15,
+    "8": 16,
+    "0": 17,
+    "27": 18,
+    "14": 19,
+    "21": 20,
+    "1": 21,
+    "23": 22,
+    "12": 23
+  },
+  "16": {
+    "31": 0,
+    "30": 1,
+    "15": 2,
+    "11": 3,
+    "24": 4,
+    "5": 5,
+    "0": 6,
+    "18": 7,
+    "20": 8,
+    "10": 9,
+    "21": 10,
+    "4": 11,
+    "2": 12,
+    "17": 13,
+    "9": 14,
+    "14": 15,
+    "22": 16,
+    "12": 17,
+    "1": 18,
+    "29": 19,
+    "28": 20,
+    "3": 21,
+    "26": 22,
+    "27": 23
+  },
+  "17": {
+    "14": 0,
+    "30": 1,
+    "5": 2,
+    "4": 3,
+    "17": 4,
+    "11": 5,
+    "28": 6,
+    "7": 7,
+    "25": 8,
+    "8": 9,
+    "12": 10,
+    "13": 11,
+    "2": 12,
+    "19": 13,
+    "24": 14,
+    "0": 15,
+    "22": 16,
+    "27": 17,
+    "16": 18,
+    "10": 19,
+    "21": 20,
+    "26": 21,
+    "3": 22,
+    "15": 23
+  },
+  "18": {
+    "1": 0,
+    "18": 1,
+    "24": 2,
+    "14": 3,
+    "15": 4,
+    "27": 5,
+    "20": 6,
+    "23": 7,
+    "9": 8,
+    "7": 9,
+    "2": 10,
+    "13": 11,
+    "31": 12,
+    "16": 13,
+    "26": 14,
+    "6": 15,
+    "19": 16,
+    "12": 17,
+    "0": 18,
+    "30": 19,
+    "5": 20,
+    "29": 21,
+    "11": 22,
+    "10": 23
+  },
+  "19": {
+    "3": 0,
+    "19": 1,
+    "6": 2,
+    "29": 3,
+    "16": 4,
+    "31": 5,
+    "7": 6,
+    "0": 7,
+    "17": 8,
+    "12": 9,
+    "2": 10,
+    "13": 11,
+    "15": 12,
+    "22": 13,
+    "20": 14,
+    "9": 15,
+    "10": 16,
+    "25": 17,
+    "11": 18,
+    "23": 19,
+    "18": 20,
+    "24": 21,
+    "4": 22,
+    "28": 23
+  },
+  "20": {
+    "22": 0,
+    "16": 1,
+    "30": 2,
+    "24": 3,
+    "31": 4,
+    "21": 5,
+    "11": 6,
+    "12": 7,
+    "0": 8,
+    "13": 9,
+    "7": 10,
+    "25": 11,
+    "23": 12,
+    "10": 13,
+    "6": 14,
+    "5": 15,
+    "4": 16,
+    "20": 17,
+    "26": 18,
+    "1": 19,
+    "8": 20,
+    "2": 21,
+    "15": 22,
+    "29": 23
+  },
+  "21": {
+    "3": 0,
+    "9": 1,
+    "27": 2,
+    "21": 3,
+    "6": 4,
+    "1": 5,
+    "2": 6,
+    "20": 7,
+    "31": 8,
+    "18": 9,
+    "10": 10,
+    "14": 11,
+    "13": 12,
+    "30": 13,
+    "29": 14,
+    "7": 15,
+    "23": 16,
+    "8": 17,
+    "28": 18,
+    "11": 19,
+    "4": 20,
+    "24": 21,
+    "25": 22,
+    "16": 23
+  },
+  "22": {
+    "25": 0,
+    "16": 1,
+    "14": 2,
+    "8": 3,
+    "18": 4,
+    "22": 5,
+    "15": 6,
+    "4": 7,
+    "0": 8,
+    "20": 9,
+    "13": 10,
+    "26": 11,
+    "27": 12,
+    "23": 13,
+    "7": 14,
+    "19": 15,
+    "5": 16,
+    "31": 17,
+    "21": 18,
+    "29": 19,
+    "11": 20,
+    "1": 21,
+    "6": 22,
+    "17": 23
+  },
+  "23": {
+    "31": 0,
+    "18": 1,
+    "10": 2,
+    "16": 3,
+    "0": 4,
+    "22": 5,
+    "28": 6,
+    "17": 7,
+    "8": 8,
+    "3": 9,
+    "14": 10,
+    "19": 11,
+    "25": 12,
+    "27": 13,
+    "13": 14,
+    "24": 15,
+    "23": 16,
+    "4": 17,
+    "7": 18,
+    "6": 19,
+    "20": 20,
+    "21": 21,
+    "26": 22,
+    "30": 23
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0"
+}

model-00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db530d47948960d23da26da2d803e75c1f941419e1155b41a07ae88d8db7aa6b
+size 1211506816

model-00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2096bb836d90d026cf3eee7242c4c72aa5f265f1c840bf1a64f3984101911a59
+size 1248060360

model-00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36633929c9834355dd5ea29c9ada0e529df4a3326d26642bb474b36676c605d3
+size 1248060360

model-00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5217657e0208159003f6c724d1d62066bf064f102700206e4ef564c5a2f104c7
+size 1248060360

model-00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da46ebdef8475f9c9c135fb43c977f5f5810dafea0cb91d5391066fd01087ab3
+size 1248060360

model-00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7d8874765d6399b0d0673a87a0ef7b0b414ab6b84bb40d3983bf0ca47efb88
+size 1248060360

model-00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d363bfc52905b767ac45dff6b110f66ea6d3d8b508e785bee0255d1dd3cdb7
+size 1248060360

model-00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be799e61dc9e6540c47e92f4d02b387b80020d807d38cfb8fde009da7cc42a88
+size 1248060360

model-00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429ab1743cfe5c27e9ce6de38bc266ded270ab61a756e41eab395402ff92c524
+size 1248060360

model-00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38728b215aa24c6bda898d75455f2960bbe90ac38b249896ec18d5c8b8474748
+size 1248060360

model-00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea229c25dff40964059456e229dc4b895820e9376a801653eb6f15555b244d4
+size 1248060312

model-00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3605228886fed93d5a9cf8828c55dd844a10a4f59a21bbdfec59bdba615a990d
+size 1248060376

model-00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bab3f9906501501d5259a6c60243ee7c55fdbe8273ea30c4e228c4d75aa347e
+size 1248060376

model-00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e167cf64ced8e2a532767b5d7461f17b76775764bfab330bb6d58129a9c1eb
+size 1248060376

model-00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcd90df463db31cbc158ab6304b55dab67a4a97f6f544ce9bb1f6bb4754c12
+size 1248060376

model-00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d9887418886007f8b6a26a2d29f6ec7d0c07c061aa67f6cb2eb1a2ddab0fb5
+size 1248060376

model-00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1ac3e33e146871bed14e095291ea03a72879d2bb8c5f6d16fa38150b3832fe
+size 1248060376

model-00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773b42e855514c9a06f44c1efd1600dc5a3b24022bd09592152584045563ca20
+size 1248060376

model-00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83fde7e511d803820dd72990807b7012ffc980642f653f929a64c4439c5cb75
+size 1248060376

model-00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981f50cee7ed22edf8ba3e06cd3dac4c2699c3f0eed189078dcac429fdf368a6
+size 1248060376

model-00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b874941d496a260a43ef6ea0a3ee0f87b45598d7879f73282ae60e5d47edbc
+size 1248060376

model-00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786cc0f0c3ffcbf6d956bf60f1b92c523d756eba4e241eed1f93131757396f53
+size 1248060376

model-00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db82d558366860d639557358f71037faccd3236d0fff8be7561ccd2b3e24d19d
+size 1248060376

model-00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b70d6b9c828ca28c71b5e14b2fdfc3d00c00c96dd7026588eefec2b9d21a60
+size 1248060376

model-00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05b403fc66b41f6bfded66aeef80c86be8d10b72b3859162603f3b087b98109
+size 1194826424

model-00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e257de1fa16cf80c8a36ca29c5974fc999f0dc7ada1468bfd0be18151af482
+size 1158267008

model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 16134970752,
+    "total_size": 32269941504
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00026-of-00026.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00026.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00026.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00002-of-00026.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00002-of-00026.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00026.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00002-of-00026.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00026.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00026.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00026.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00026.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00026.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00003-of-00026.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00003-of-00026.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00002-of-00026.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00002-of-00026.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00026.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00026.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00012-of-00026.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00012-of-00026.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00012-of-00026.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00011-of-00026.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00011-of-00026.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00026.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00026.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00026.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00013-of-00026.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00013-of-00026.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00013-of-00026.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00013-of-00026.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00013-of-00026.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00012-of-00026.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00012-of-00026.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00026.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00026.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00014-of-00026.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00014-of-00026.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00014-of-00026.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00013-of-00026.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00013-of-00026.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00026.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00026.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00026.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00015-of-00026.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00015-of-00026.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00015-of-00026.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00015-of-00026.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00015-of-00026.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00014-of-00026.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00014-of-00026.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00026.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00026.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00016-of-00026.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00016-of-00026.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00016-of-00026.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00015-of-00026.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00015-of-00026.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00026.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00026.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00026.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00017-of-00026.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00017-of-00026.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00017-of-00026.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00017-of-00026.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00017-of-00026.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00016-of-00026.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00016-of-00026.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00026.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00026.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00018-of-00026.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00018-of-00026.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00018-of-00026.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00018-of-00026.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00017-of-00026.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00017-of-00026.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00026.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00026.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00026.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00019-of-00026.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00019-of-00026.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00019-of-00026.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00019-of-00026.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00018-of-00026.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00018-of-00026.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00026.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00026.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00020-of-00026.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00020-of-00026.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00020-of-00026.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00019-of-00026.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00019-of-00026.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00026.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00026.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00026.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00026.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00021-of-00026.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00021-of-00026.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00021-of-00026.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00021-of-00026.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00020-of-00026.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00020-of-00026.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00026.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00026.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00026.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00004-of-00026.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00004-of-00026.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00003-of-00026.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00003-of-00026.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00026.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00026.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00022-of-00026.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00022-of-00026.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00022-of-00026.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00021-of-00026.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00021-of-00026.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00026.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00026.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00023-of-00026.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00023-of-00026.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00023-of-00026.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00022-of-00026.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00022-of-00026.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00026.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00026.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00024-of-00026.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00024-of-00026.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00024-of-00026.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00023-of-00026.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00023-of-00026.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00026.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00026.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00025-of-00026.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00025-of-00026.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00025-of-00026.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00025-of-00026.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00024-of-00026.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00024-of-00026.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00026.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00026.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00026.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00026.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00005-of-00026.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00005-of-00026.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00004-of-00026.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00004-of-00026.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00026.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00026.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00026.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00006-of-00026.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00006-of-00026.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00005-of-00026.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00005-of-00026.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00026.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00026.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00026.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00007-of-00026.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00007-of-00026.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00007-of-00026.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00007-of-00026.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00007-of-00026.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00006-of-00026.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00006-of-00026.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00026.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00026.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00026.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00008-of-00026.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00008-of-00026.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00008-of-00026.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00007-of-00026.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00007-of-00026.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00026.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00026.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00026.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00009-of-00026.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00009-of-00026.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00009-of-00026.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00009-of-00026.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00008-of-00026.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00008-of-00026.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00026.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00026.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00026.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00010-of-00026.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00010-of-00026.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00010-of-00026.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00009-of-00026.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00009-of-00026.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00026.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00026.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00026.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00026.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00011-of-00026.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00011-of-00026.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00011-of-00026.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00010-of-00026.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00010-of-00026.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00026.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00026.safetensors",
+    "model.norm.weight": "model-00025-of-00026.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}