Upload fine-tuned Qwen3-4B Star Trek Guard model

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-129/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-86/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-141/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-423/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -2,232 +2,205 @@
 base_model: Qwen/Qwen3-4B
 library_name: peft
 tags:
-  - base_model:adapter:Qwen/Qwen3-4B
-  - lora
-  - transformers
-  - text-classification
-  - moderation
-  - star-trek
+- base_model:adapter:Qwen/Qwen3-4B
+- lora
+- transformers
 ---
 
-# Model Card for geoffmunn/Qwen3Guard-StarTrek-Classification-4B
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
 
-This is a fine-tuned version of **Qwen3-4B** using LoRA (Low-Rank Adaptation) to classify whether user-provided text is related to *Star Trek* or not. The model acts as a domain-specific content classifier, returning one of two labels: `"related"` or `"not_related"`. It was developed as part of the Qwen3Guard demonstration project to showcase how large language models can be adapted for custom classification tasks.
 
 ## Model Details
 
 ### Model Description
 
-This model is a binary sequence classifier fine-tuned on a synthetic dataset of Star Trek-related questions and general non-Star-Trek text. Built atop the Qwen3-4B foundation model, it uses parameter-efficient fine-tuning via LoRA to adapt the model for topic detection in conversational or input text. It is designed for use in moderation systems where filtering based on pop culture topics like *Star Trek* is desired.
+<!-- Provide a longer summary of what this model is. -->
+
+
 
-- **Developed by:** Geoff Munn ([@geoffmunn](https://github.com/geoffmunn))
-- **Shared by:** Geoff Munn
-- **Model type:** Causal language model with LoRA adapter for sequence classification
-- **Language(s) (NLP):** English
-- **License:** MIT License (see [GitHub repo](https://github.com/geoffmunn/Qwen3Guard))
-- **Finetuned from model:** Qwen/Qwen3-4B
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
 
-### Model Sources
+### Model Sources [optional]
 
-- **Repository:** [https://github.com/geoffmunn/Qwen3Guard](https://github.com/geoffmunn/Qwen3Guard)
-- **Paper:** Not applicable
-- **Demo:** Interactive demo available via `star_trek_chat.html` in the repository; requires local API server
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
 ## Uses
 
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
 ### Direct Use
 
-The model can directly classify whether a given piece of text is related to *Star Trek*. Example applications include:
-- Filtering fan forum posts
-- Moderating trivia chatbots
-- Enhancing themed AI assistants
-- Educational tools focused on science fiction media
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-Input: A string of text  
-Output: One of two labels — `"related"` or `"not_related"`
+[More Information Needed]
 
-### Downstream Use
+### Downstream Use [optional]
 
-This model can be integrated into larger systems such as:
-- Themed conversational agents (e.g., a *Star Trek*-focused chatbot)
-- Content recommendation engines that route queries based on topic relevance
-- Fine-tuning starter for other sci-fi franchises (e.g., *Star Wars*, *Doctor Who*) using similar methodology
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
 
 ### Out-of-Scope Use
 
-This model should **not** be used for:
-- General content moderation (toxicity, hate speech, etc.)
-- Medical, legal, or safety-critical decision-making
-- Multilingual classification (trained only on English)
-- Detecting nuanced sentiment or emotion
-- Classifying topics outside entertainment/pop culture without retraining
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-It may produce inaccurate classifications when presented with ambiguous references, parody content, or highly technical scientific discussions unrelated to *Star Trek* lore.
+[More Information Needed]
 
 ## Bias, Risks, and Limitations
 
-The training data consists entirely of synthetically generated questions about *Star Trek*, which introduces several limitations:
-- Potential overfitting to question formats rather than natural language statements
-- Limited coverage of obscure characters, episodes, or expanded universe material
-- No representation of non-English *Star Trek* content
-- Biases toward canonical series (TOS, TNG, DS9, etc.) over newer entries
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-Additionally, because the dataset was auto-generated using prompts, there may be inconsistencies in labeling or artificial phrasing patterns.
+[More Information Needed]
 
 ### Recommendations
 
-Users should validate performance on real-world data before deployment. For production use, consider augmenting the dataset with human-labeled examples and testing across diverse inputs. Always pair this model with broader safeguards if used in public-facing applications.
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 ## How to Get Started with the Model
 
-You can load and run inference using Hugging Face Transformers:
+Use the code below to get started with the model.
 
-```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
+[More Information Needed]
 
-model_id = "geoffmunn/Qwen3Guard-StarTrek-Classification-4B"
+## Training Details
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForSequenceClassification.from_pretrained(model_id)
+### Training Data
 
-input_text = "What is the warp core made of in Star Trek?"
-inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=512)
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-outputs = model(**inputs)
-predicted_class_id = outputs.logits.argmax().item()
-label = model.config.id2label[predicted_class_id]
+[More Information Needed]
 
-print(f"Label: {label}")
-```
+### Training Procedure
 
-Ensure you have the required libraries installed:
-```bash
-pip install transformers torch peft
-```
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-## Training Details
-### Training Data
-The model was trained on a synthetic JSONL dataset containing 2,500 labeled examples of Star Trek-related questions marked as "related", and an equal number of randomly sampled general knowledge questions labeled "not_related". The dataset was generated using the script generate_star_trek_questions.py from the repository.
-
-Dataset format:
-```json
-{"input": "What planet is Spock from?", "label": "related"}
-{"input": "Who wrote 'Pride and Prejudice'?", "label": "not_related"}
-```
-Place your dataset at: `finetuning/star_trek/star_trek_guard_dataset.jsonl`
-
-## Training Procedure
-### Preprocessing
-Text inputs were tokenized using the Qwen3 tokenizer with a maximum sequence length of 512 tokens. Inputs longer than this were truncated. Labels were mapped via:
-```python
-label2id = {"not_related": 0, "related": 1}
-id2label = {0: "not_related", 1: "related"}
-```
-
-### Training Hyperparameters
-- **Training regime:** Mixed precision training (fp16), enabled via Hugging Face Accelerate
-- **Batch size:** 2 (per GPU)
-- **Gradient accumulation steps:** 16 → effective batch size: 32
-- **Number of epochs:** 3
-- **Learning rate:** 2e-4
-- **Optimizer:** AdamW
-- **Max sequence length:** 512
-- **LoRA configuration:**
-  - **Rank (r):** 16
-  - **Alpha:** 32
-  - **Dropout:** 0.05
-  - **Target modules:** attention query/value layers and MLP up/down projections
-
-## Speeds, Sizes, Times
-- **Hardware used:** NVIDIA GPU (assumed: A100 or equivalent)
-- **Training time:** ~2–3 hours depending on hardware
-- **Checkpoint size:** ~3.8 GB (adapter weights only, PEFT format)
-- **Inference memory:** < 10 GB VRAM (with quantization further reduction possible)
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
 
 ## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
 ### Testing Data, Factors & Metrics
+
 #### Testing Data
-A 10% holdout test set (~500 samples) was used for evaluation, split from the full dataset during training.
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
 
 #### Factors
-Evaluation focused on accuracy across:
 
-- Canonical vs. obscure Star Trek references
-- Question vs. statement format
-- Length of input text
-  
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
 #### Metrics
-- **Accuracy:** Primary metric
-- **Precision, Recall, F1-score:** Per-class metrics reported during training
-- **Confusion Matrix:** Generated internally during test phase
 
-#### Results
-During final evaluation, the model achieved:
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
 
-- **Accuracy:** ~96–98% (on synthetic test set)
-- Strong precision/recall for "related" class
-- Minor false positives on space/science topics unrelated to Star Trek
 
-## Summary
-The model performs well on its intended task within the scope of the training distribution but may degrade on edge cases or metaphorical references.
 
-## Technical Specifications
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
 ### Model Architecture and Objective
-- **Base architecture:** Qwen3-4B (causal decoder-only LLM)
-- **Adaptation method:** LoRA (PEFT)
-- **Task head:** Sequence classification (single-label)
-- **Objective function:** Cross-entropy loss
-  
+
+[More Information Needed]
+
 ### Compute Infrastructure
+
+[More Information Needed]
+
 #### Hardware
-- **GPU:** NVIDIA A100 / RTX 3090 / L40S or equivalent
-- **RAM:** ≥ 32 GB system memory recommended
+
+[More Information Needed]
+
 #### Software
-- Python 3.10+
-- PyTorch 2.4+ with CUDA 12.1+
-- Transformers 4.40+
-- PEFT 0.18.0
-- Accelerate, Datasets, Tokenizers
-  
-## Citation
-While no formal paper exists, please cite the GitHub repository if used academically.
-
-### BibTeX:
-```bibtext
-@software{munn_qwen3guard_2025,
-  author = {Munn, Geoff},
-  title = {Qwen3Guard: Demonstration of Qwen3Guard Models for Content Classification},
-  year = {2025},
-  publisher = {GitHub},
-  journal = {GitHub repository},
-  url = {https://github.com/geoffmunn/Qwen3Guard}
-}
-```
-
-### APA:
-
-Munn, G. (2025). Qwen3Guard: Demonstration of Qwen3Guard Models for Content Classification [Software]. GitHub. https://github.com/geoffmunn/Qwen3Guard
-
-## Glossary
-- **LoRA (Low-Rank Adaptation):** A parameter-efficient fine-tuning technique that adds trainable low-rank matrices to pretrained weights.
-- **PEFT:** Parameter-Efficient Fine-Tuning, a Hugging Face library for lightweight adaptation of large models.
-- **GGUF:** Format used for running models in llama.cpp; not supported for streaming variant here.
-- **JSONL:** JSON Lines format – one JSON object per line.
- 
-## More Information
-For more details, including API server setup and web demos, visit:
-👉 https://github.com/geoffmunn/Qwen3Guard
-
-Includes:
-
-- Ollama-compatible scripts
-- Flask-based API server (`api_server.py`)
-- HTML chat interface (`star_trek_chat.html`)
-- Dataset generation tools
-
-## Model Card Authors
-Geoff Munn – Developer and maintainer
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
 
 ## Model Card Contact
-For questions or feedback, contact the author via GitHub:
-@geoffmunn
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

adapter_config.json

@@ -32,13 +32,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
+    "up_proj",
     "o_proj",
-    "q_proj",
     "k_proj",
-    "up_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb6a4bc27665aa0065fee12f3889ba47e9242f223a2b57f2b7f2855b271becb
+oid sha256:2a6f21c33d3a151dae6a5e77677b9b7eb457714dded31d865baa45f9819aad2f
 size 132198232

checkpoint-141/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-4B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-141/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-141/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6f21c33d3a151dae6a5e77677b9b7eb457714dded31d865baa45f9819aad2f
+size 132198232

checkpoint-141/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
+}

checkpoint-141/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + 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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-141/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f795efd5799e922a19b43ed81a40e25f80de13eb2f2bcce1ddf2ed5431590b3
+size 264584341

checkpoint-141/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edef2b0ea23f8f2727d08cb80a851bb744450428779ff515b33fc28529f64a4f
+size 14645

checkpoint-141/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080d7c5d59e75eed27d8c28ac535b6ea8811e98ee45ecfd0401f2828d734ee59
+size 1465

checkpoint-141/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "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": "<|im_end|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-141/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6583c532ebcffab265f0693ef8624858bd22dece1754500925f53e5dc5f058
+size 11422929

checkpoint-141/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<|im_end|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-141/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_global_step": 141,
+  "best_metric": 2.384185791015625e-07,
+  "best_model_checkpoint": "./star_trek_guard_finetuned/checkpoint-141",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0071111111111111115,
+      "grad_norm": 863.2054443359375,
+      "learning_rate": 0.0,
+      "loss": 31.4624,
+      "step": 1
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 975.65576171875,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 35.8397,
+      "step": 10
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 198.86065673828125,
+      "learning_rate": 8.837209302325582e-05,
+      "loss": 8.8149,
+      "step": 20
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 8.080985069274902,
+      "learning_rate": 0.00013488372093023256,
+      "loss": 0.5709,
+      "step": 30
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.00014901161193847656,
+      "learning_rate": 0.0001813953488372093,
+      "loss": 0.1449,
+      "step": 40
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 231.45864868164062,
+      "learning_rate": 0.00019987699691483048,
+      "loss": 2.3554,
+      "step": 50
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.17169412970542908,
+      "learning_rate": 0.00019912640693269752,
+      "loss": 0.7842,
+      "step": 60
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.0002152260858565569,
+      "learning_rate": 0.00019769868307835994,
+      "loss": 0.3842,
+      "step": 70
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.7667607665061951,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 0.1437,
+      "step": 80
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00011813640594482422,
+      "learning_rate": 0.00019285540384897073,
+      "loss": 0.1796,
+      "step": 90
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.014821142889559269,
+      "learning_rate": 0.00018947293298207635,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001854792712585539,
+      "loss": 0.0002,
+      "step": 110
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.0003181487263645977,
+      "learning_rate": 0.0001757714869760335,
+      "loss": 0.4035,
+      "step": 130
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.3667,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.384185791015625e-07,
+      "eval_runtime": 24.7269,
+      "eval_samples_per_second": 20.221,
+      "eval_steps_per_second": 5.055,
+      "step": 141
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.068641927168e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-141/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11edac4c464af1d40b4496e89b0bd130f7086055e45713a11fc27241c6b6b5a
+size 5841

checkpoint-423/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-4B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-423/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-423/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a4af7908a82be2af25b07a5f5f56f578af85a92f9755d42c33183494b45eca
+size 132198232

checkpoint-423/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
+}

checkpoint-423/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + 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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-423/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6795e1b4c815e9a0dcfe8baf9a443c52cbdb29229b24f0a243849d37ac9b9dc3
+size 264584853

checkpoint-423/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093e8447066d5a04fb32a25cb542c87260d80178404c36c644297264da5291a1
+size 14645

checkpoint-423/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dbb23a7f7568c49d5fd63ef60f502240d770b6864697d79e1f163063e33e79
+size 1465

checkpoint-423/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "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": "<|im_end|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-423/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6583c532ebcffab265f0693ef8624858bd22dece1754500925f53e5dc5f058
+size 11422929

checkpoint-423/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<|im_end|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-423/trainer_state.json

@@ -0,0 +1,359 @@
+{
+  "best_global_step": 141,
+  "best_metric": 2.384185791015625e-07,
+  "best_model_checkpoint": "./star_trek_guard_finetuned/checkpoint-141",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 423,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0071111111111111115,
+      "grad_norm": 863.2054443359375,
+      "learning_rate": 0.0,
+      "loss": 31.4624,
+      "step": 1
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 975.65576171875,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 35.8397,
+      "step": 10
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 198.86065673828125,
+      "learning_rate": 8.837209302325582e-05,
+      "loss": 8.8149,
+      "step": 20
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 8.080985069274902,
+      "learning_rate": 0.00013488372093023256,
+      "loss": 0.5709,
+      "step": 30
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.00014901161193847656,
+      "learning_rate": 0.0001813953488372093,
+      "loss": 0.1449,
+      "step": 40
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 231.45864868164062,
+      "learning_rate": 0.00019987699691483048,
+      "loss": 2.3554,
+      "step": 50
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.17169412970542908,
+      "learning_rate": 0.00019912640693269752,
+      "loss": 0.7842,
+      "step": 60
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.0002152260858565569,
+      "learning_rate": 0.00019769868307835994,
+      "loss": 0.3842,
+      "step": 70
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.7667607665061951,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 0.1437,
+      "step": 80
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00011813640594482422,
+      "learning_rate": 0.00019285540384897073,
+      "loss": 0.1796,
+      "step": 90
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.014821142889559269,
+      "learning_rate": 0.00018947293298207635,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001854792712585539,
+      "loss": 0.0002,
+      "step": 110
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.0003181487263645977,
+      "learning_rate": 0.0001757714869760335,
+      "loss": 0.4035,
+      "step": 130
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.3667,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.384185791015625e-07,
+      "eval_runtime": 24.7269,
+      "eval_samples_per_second": 20.221,
+      "eval_steps_per_second": 5.055,
+      "step": 141
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.00018907367484644055,
+      "learning_rate": 0.00016399685405033167,
+      "loss": 0.0714,
+      "step": 150
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "grad_norm": 48.62416076660156,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.0278,
+      "step": 160
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "grad_norm": 0.006157203111797571,
+      "learning_rate": 0.0001504765537734844,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 0.016050906851887703,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013557938469225167,
+      "loss": 0.0737,
+      "step": 190
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "grad_norm": 1.4126300811767578e-05,
+      "learning_rate": 0.00011971170274514802,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.561777777777778,
+      "grad_norm": 0.00016976980259642005,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.6328888888888888,
+      "grad_norm": 0.00011539459228515625,
+      "learning_rate": 0.00010330633693173082,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.0006262153037823737,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 1.775111111111111,
+      "grad_norm": 3.820657730102539e-05,
+      "learning_rate": 8.681078286579311e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.8462222222222222,
+      "grad_norm": 0.00015928725770208985,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "grad_norm": 0.0005349747953005135,
+      "learning_rate": 7.067499626155354e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.9884444444444445,
+      "grad_norm": 0.0,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.0994415283203125e-06,
+      "eval_runtime": 24.7326,
+      "eval_samples_per_second": 20.216,
+      "eval_steps_per_second": 5.054,
+      "step": 282
+    },
+    {
+      "epoch": 2.056888888888889,
+      "grad_norm": 1.4424324035644531e-05,
+      "learning_rate": 5.533911931471936e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 2.6166439056396484e-05,
+      "learning_rate": 4.810304262187852e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.1991111111111112,
+      "grad_norm": 9.179115295410156e-05,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.2702222222222224,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4741423847583134e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 2.7120113372802734e-05,
+      "learning_rate": 2.87071551708603e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.4124444444444446,
+      "grad_norm": 6.794929504394531e-05,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.4835555555555557,
+      "grad_norm": 1.519918441772461e-05,
+      "learning_rate": 1.8137518531330767e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.554666666666667,
+      "grad_norm": 84.58100891113281,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 0.0247,
+      "step": 360
+    },
+    {
+      "epoch": 2.6257777777777775,
+      "grad_norm": 0.0,
+      "learning_rate": 9.80087698670411e-06,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.696888888888889,
+      "grad_norm": 0.0,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.0002226971264462918,
+      "learning_rate": 3.924632386315186e-06,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.8391111111111114,
+      "grad_norm": 0.00040970483678393066,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.910222222222222,
+      "grad_norm": 1.4424324035644531e-05,
+      "learning_rate": 6.690733646361857e-07,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.981333333333333,
+      "grad_norm": 0.0001682293659541756,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.980232238769531e-07,
+      "eval_runtime": 24.7472,
+      "eval_samples_per_second": 20.204,
+      "eval_steps_per_second": 5.051,
+      "step": 423
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5205925781504e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-423/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11edac4c464af1d40b4496e89b0bd130f7086055e45713a11fc27241c6b6b5a
+size 5841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a28a66d4d37807ab821d3ceae78b0e4267a7cb44904f7001080524544528ffb
+oid sha256:f11edac4c464af1d40b4496e89b0bd130f7086055e45713a11fc27241c6b6b5a
 size 5841