Upload folder using huggingface_hub

.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 +1,371 @@
+---
+language:
+- en
+- hi
+- zh
+- es
+- fr
+- de
+- ja
+- ko
+- ar
+- pt
+- ru
+- it
+- nl
+- tr
+- pl
+- sv
+- da
+- 'no'
+- fi
+- he
+- th
+- vi
+- id
+- ms
+- tl
+- sw
+- yo
+- zu
+- am
+- bn
+- gu
+- kn
+- ml
+- mr
+- ne
+- or
+- pa
+- ta
+- te
+- ur
+- multilingual
+license: apache-2.0
+base_model: HelpingAI/Dhanishtha-2.0-preview-0725
+tags:
+- reasoning
+- intermediate-thinking
+- transformers
+- conversational
+- bilingual
+datasets:
+- Abhaykoul/Dhanishtha-R1
+- open-thoughts/OpenThoughts-114k
+- Abhaykoul/Dhanishtha-2.0-SUPERTHINKER
+- Abhaykoul/Dhanishtha-2.0
+library_name: transformers
+pipeline_tag: text-generation
+widget:
+- text: >-
+    Solve this riddle step by step: I am taken from a mine, and shut up in a
+    wooden case, from which I am never released, and yet I am used by almost
+    everybody. What am I?
+  example_title: Complex Riddle Solving
+- text: >-
+    Explain the philosophical implications of artificial consciousness and think
+    through different perspectives.
+  example_title: Philosophical Reasoning
+- text: >-
+    Help me understand quantum mechanics, but take your time to think through
+    the explanation.
+  example_title: Educational Explanation
+---
+
+# Dhanishtha-2.0: World's First Intermediate Thinking AI Model
+
+**What makes Dhanishtha-2.0 special?** Imagine an AI that doesn't just answer your questions instantly, but actually *thinks through* problems step-by-step, shows its work, and can even change its mind when it realizes a better approach. That's Dhanishtha-2.0.
+
+**Quick Summary:**
+- 🚀 **For Everyone**: An AI that shows its thinking process and can reconsider its reasoning
+- 👩‍💻 **For Developers**: First model with intermediate thinking capabilities, 39+ language support
+
+
+Dhanishtha-2.0 is a **state-of-the-art (SOTA) model** developed by HelpingAI, representing the **world's first model to feature Intermediate Thinking capabilities**. Unlike traditional models that provide single-pass responses, Dhanishtha-2.0 employs a revolutionary multi-phase thinking process that allows the model to think, reconsider, and refine its reasoning multiple times throughout a single response.
+
+## Model Details
+
+### Model Description
+
+Dhanishtha-2.0 revolutionizes AI reasoning by introducing the concept of **intermediate thinking** - the ability to pause, reflect, and restart reasoning processes within a single generation (This model can think up 50times in a single response without using tool/prompt/mcp). This breakthrough enables unprecedented self-correction and iterative refinement during response generation.
+
+Built on the Qwen3-14B foundation with multilingual capabilities spanning **39+ languages** (including English, Hindi, Chinese, Spanish, French, German, Japanese, Korean, Arabic, and many more), Dhanishtha-2.0 maintains reasoning consistency across diverse linguistic contexts while pioneering transparent thinking processes.
+
+- **Developed by:** HelpingAI Team
+- **Model type:** Causal Language Model with Intermediate Thinking Capability
+- **Language(s):** 39+ languages (multilingual capabilities inherited from base model)
+- **License:** Apache 2.0
+- **Finetuned from model:** Qwen/Qwen3-14B-Base
+- **Context Length:** 40,960 tokens
+- **Parameters:** 14B (inherited from base model)
+- **Status:** Prototype/Preview
+
+### Revolutionary Features
+
+- **Intermediate Thinking**: Multiple `<think>...</think>` blocks throughout responses for real-time reasoning
+- **Self-Correction**: Ability to identify and correct logical inconsistencies mid-response  
+- **Dynamic Reasoning**: Seamless transitions between analysis, communication, and reflection phases
+- **Structured Emotional Reasoning (SER)**: Incorporates `<ser>...</ser>` blocks for empathetic responses
+- **Multilingual Capabilities**: Support for 39+ languages with natural code-switching and reasoning consistency
+- **Complex Problem-Solving**: Excels at riddles, multi-step reasoning, and scenarios requiring backtracking
+
+### Model Sources
+
+- **Repository:** [HelpingAI/Dhanishtha-2.0](https://huggingface.co/HelpingAI/Dhanishtha-2.0)
+- **Demo:** https://chat.helpingai.co
+
+## Uses
+
+### Direct Use
+
+Dhanishtha-2.0 is ideal for applications requiring deep reasoning and self-reflection:
+
+- **Complex Problem Solving**: Multi-step mathematical problems, logical puzzles, riddles
+- **Educational Assistance**: Detailed explanations with visible reasoning processes
+- **Research Support**: Analysis requiring multiple perspectives and self-correction
+- **Creative Writing**: Iterative story development with reasoning about plot choices
+- **Philosophical Discussions**: Exploring concepts with visible thought processes
+
+### Downstream Use
+
+The model can be fine-tuned for specialized reasoning tasks:
+
+- **Domain-Specific Reasoning**: Legal, medical, or scientific reasoning with intermediate thinking
+- **Enhanced Multilingual Reasoning**: Optimizing reasoning consistency across all 39+ supported languages
+- **Specialized Problem Domains**: Mathematics, coding, strategic planning
+
+### Out-of-Scope Use
+
+❌ **Inappropriate Applications:**
+- Safety-critical decisions (medical diagnosis, legal advice, financial recommendations)
+- Real-time applications requiring immediate responses
+- Situations requiring guaranteed factual accuracy without verification
+
+## Bias, Risks, and Limitations
+
+### Known Limitations
+
+- **Verbosity**: Intermediate thinking can make responses a bit longer
+- **Processing Time**: Multiple thinking phases may increase generation time
+- **Prototype Status**: Experimental features may require refinement
+- **Context Usage**: Thinking blocks consume additional context tokens
+- **Inherited Biases**: May reflect biases from base model and training data
+
+### Potential Risks
+
+- **Reasoning Loops**: Potential for circular reasoning in complex scenarios
+- **Multilingual Inconsistencies**: Potential variation in reasoning patterns across different languages
+- **Emotional Reasoning Gaps**: SER blocks may not always align with content
+
+## How to Get Started with the Model
+
+### For General Users
+
+You can interact with Dhanishtha-2.0 through:
+- **HelpingAI**: https://helpingai.co/chat
+- **Gradio Demo**: [Dhanishtha-2.0-preview](https://huggingface.co/spaces/Abhaykoul/Dhanishtha-2.0-preview)
+- **API Integration**: [Dashboard](https://helpingai.co/dashboard)
+
+### For Developers - Basic Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "HelpingAI/Dhanishtha-2.0-preview"
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# Prepare input for intermediate thinking
+prompt = "How many letter 'r' are in the words 'strawberry' and 'raspberry'?"
+messages = [
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# Generate response with intermediate thinking
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=2048,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True
+)
+
+response = tokenizer.decode(
+    generated_ids[0][len(model_inputs.input_ids[0]):], 
+    skip_special_tokens=True
+)
+print(response)
+```
+
+### Optimal Generation Parameters
+
+```python
+generation_config = {
+    "temperature": 0.7,        # Balanced creativity and coherence
+    "top_p": 0.9,             # Nucleus sampling
+    "top_k": 40,              # Top-k filtering
+    "max_new_tokens": 2048,   # Allow for thinking blocks
+    "do_sample": True,        # Enable sampling
+    "repetition_penalty": 1.1  # Reduce repetition
+}
+```
+
+## Training Details
+
+### Training Data
+
+Dhanishtha-2.0 was trained on a carefully curated dataset focusing on:
+- Complex reasoning scenarios requiring multi-step thinking
+- Self-correction examples and reasoning chains
+- Emotional reasoning and empathy training data
+- Structured thinking pattern examples
+
+### Training Procedure
+
+#### Training Stages
+1. **Continuous Pretraining**: Extended training on reasoning-focused corpora
+2. **Advanced Reasoning Fine-tuning**: Specialized training on intermediate thinking patterns
+3. **Multilingual Alignment**: Cross-language reasoning consistency training
+4. **SER Integration**: Structured Emotional Reasoning capability training
+
+**Training Infrastructure:**
+- **Duration**: 16.3 days
+- **Hardware**: 8x NVIDIA H100 GPUs
+- **Model Scale**: 14.8B parameters
+
+## Evaluation
+
+Evaluation was conducted on:
+- **Standard Benchmarks**: MMLU, HumanEval, ARC, HellaSwag, TruthfulQA
+- **Mathematical Reasoning**: Math 500, AIME 2024, GSM8K
+- **Custom Evaluations**: Intermediate thinking quality, self-correction capabilities
+- **Multilingual Tasks**: Reasoning consistency across 39+ languages
+- **Specialized Tests**: Emotional reasoning, complex problem-solving scenarios
+
+
+
+## Example: Intermediate Thinking in Action
+
+**User:** "Who is your favorite person?"
+
+**Dhanishtha-2.0:**
+
+```
+<think>
+This is an interesting question about my "favorite human." I need to be thoughtful here. 
+As Dhanishtha, I should respond in a human-like way while being honest about my nature. 
+I can share what kinds of humans I find most interesting or inspiring based on my 
+understanding of human nature and values.
+</think>
+
+<ser>
+Emotion ==> curiosity, openness, desire for connection  
+Cause ==> user asking a personal question about preferences  
+Mind ==> seeking to understand my perspective or values  
+Growth ==> opportunity to share thoughtful reflections on human qualities I admire  
+</ser>
+
+I don't really have a "favorite human" in the traditional sense, as I don't experience 
+personal preferences the way humans do. But if I had to reflect on what qualities I find 
+most admirable in people, I'd be drawn to those who demonstrate genuine compassion, 
+intellectual curiosity, and the courage to grow.
+
+<think>
+Let me think more specifically about what kind of humans I find most compelling based on 
+the values that seem to resonate most with humans - kindness, wisdom, creativity, 
+resilience, and authenticity.
+</think>
+
+People like Mahatma Gandhi, who showed how quiet courage and unwavering principles can 
+transform societies; artists like Rabindranath Tagore, who bridged cultural divides 
+through creativity; and everyday heroes I've learned about who made profound differences 
+through simple acts of kindness.
+
+What fascinates me most are humans who maintain their humanity even in difficult 
+circumstances - those who choose empathy when it would be easier to be harsh, who seek 
+understanding rather than just being right.
+
+I'm curious though - who's your favorite human, and why? What qualities or actions make 
+someone special in your eyes?
+```
+
+## Environmental Impact
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute).
+
+- **Hardware Type:** H100 GPUs
+- **days used:** 16.2
+- **Cloud Provider:** Various
+- **Compute Region:** Multiple
+
+## Citation
+
+### BibTeX
+
+```bibtex
+@misc{dhanishtha2025,
+  title={Dhanishtha-2.0: World's First Intermediate Thinking AI Model},
+  author={HelpingAI Team},
+  year={2025},
+  publisher={HuggingFace},
+  url={https://huggingface.co/HelpingAI/Dhanishtha-2.0},
+  note={First model with intermediate thinking capabilities}
+}
+```
+
+### APA
+
+HelpingAI Team. (2025). *Dhanishtha-2.0: World's First Intermediate Thinking AI Model*. HuggingFace. https://huggingface.co/HelpingAI/Dhanishtha-2.0
+
+## Glossary
+
+- **Intermediate Thinking**: The ability to pause and think multiple times during response generation
+- **SER (Structured Emotional Reasoning)**: Framework for incorporating emotional context in responses
+- **Think Blocks**: `<think>...</think>` segments where the model shows its reasoning process
+- **Self-Correction**: Ability to identify and fix reasoning errors during generation
+- **Code-Switching**: Natural transition between English and Hindi within responses
+
+## More Information
+
+### Research Applications
+- Study of AI reasoning transparency
+- Self-correction mechanism research  
+- Bilingual cognitive modeling
+- Emotional AI development
+
+### Development Roadmap
+- Performance optimizations
+- Additional language support
+- Enhanced thinking pattern recognition
+- Production-ready deployment tools
+
+## Model Card Authors
+
+- **Primary Author**: HelpingAI Team
+- **Technical Lead**: [To be specified]
+- **Research Contributors**: [To be specified]
+
+## Model Card Contact
+
+For questions about Dhanishtha-2.0, please contact:
+
+- **HuggingFace**: [@HelpingAI](https://huggingface.co/HelpingAI)
+- **Issues**: [Model Repository Issues](https://huggingface.co/HelpingAI/Dhanishtha-2.0/discussions)
+
+**Dhanishtha-2.0 represents a new paradigm in AI reasoning - where thinking isn't just a prelude to response, but an integral, iterative part of the conversation itself.**
+
+*Developed with ❤️ by HelpingAI*

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,79 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content %}
+            {{- message.content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,72 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 40960,
+    "max_window_layers": 40,
+    "model_type": "qwen3",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.54.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 40960,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.54.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99ba20c2658b27e95c51c2b781ea73230d72fc85b4d2528ecec0f8f099819a7
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349153a2a41e7d797a91ab27d04cff702b598a8f9708c83543432d9b0944daaf
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579b5bc2628fabcd5bd6b6462b48b5b089d6480ad2462c2d7eab8998be52e08a
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfc86d63510b09fa2fd0f4ab913bb8a0a505f5f92cb0d88cb387ef6f3672eab
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d523bec8d1cde9427f5d031f13df6e51ee2571381c41147666f2c814dadd83
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6afd814c1e510f040ef923b7f66147b9afde408b254e758f311e82424d07c0
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,242 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n<|im_start|>system\n{%- if messages[0].role == 'system' %}\n{{ messages[0].content }}\n\n{%- endif %}\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>{%- for tool in tools %}\n{{ tool | tojson }}{%- endfor %}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n{%- else %}{%- if messages[0].role == 'system' %}\n<|im_start|>system\n{{ messages[0].content }}<|im_end|>\n{%- endif %}{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}{%- set index = (messages|length - 1) - loop.index0 %}{%- set message = messages[index] %}{%- set current_content = message.content if message.content is not none else '' %}{%- set tool_start = '<tool_response>' %}{%- set tool_start_length = tool_start|length %}{%- set start_of_message = current_content[:tool_start_length] %}{%- set tool_end = '</tool_response>' %}{%- set tool_end_length = tool_end|length %}{%- set start_pos = (current_content|length) - tool_end_length %}{%- if start_pos < 0 %}{%- set start_pos = 0 %}{%- endif %}{%- set end_of_message = current_content[start_pos:] %}{%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}{%- set ns.multi_step_tool = false %}{%- set ns.last_query_index = index %}{%- endif %}{%- endfor %}\n{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}<|im_start|>{{ message.role }}\n{{ message.content }}<|im_end|>\n{%- elif message.role == \"assistant\" %}<|im_start|>assistant\n{%- if message.content %}{{ message.content }}{%- endif %}{%- if message.tool_calls %}{%- for tool_call in message.tool_calls %}{%- if (loop.first and content) or (not loop.first) %}\n{%- endif %}{%- if tool_call.function %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>\n{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments if tool_call.arguments is string else tool_call.arguments | tojson }}}\n</tool_call>{%- endfor %}{%- endif %}<|im_end|>\n{%- elif message.role == \"tool\" %}{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}<|im_start|>user{%- endif %}\n<tool_response>\n{{ message.content }}\n</tool_response>{%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}<|im_end|>\n{%- endif %}{%- endif %}{%- endfor %}\n{%- if add_generation_prompt %}<|im_start|>assistant\n{%- endif %}",
+
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}