Upload LoRA adapter weights for DynastAI GRPO

README.md

@@ -3,109 +3,200 @@ base_model: unsloth/Qwen3-1.7B
 library_name: peft
 ---
 
-# Model Card for dynastai-grpo-lora
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
 
-This is a LoRA adapter for the Qwen3-1.7B model, fine-tuned using Generative Reward-based Policy Optimization (GRPO) to act as a royal advisor in the DynastAI kingdom simulation game. The model learns to select options that keep all kingdom metrics (Church, People, Military, Treasury) balanced close to 50.
 
 ## Model Details
 
 ### Model Description
 
-- **Developed by:** Slyracoon23
-- **Model type:** LoRA adapter for Qwen3-1.7B
-- **Language(s) (NLP):** English
-- **License:** [Qwen3-1.7B License](https://huggingface.co/Qwen/Qwen3-1.7B)
-- **Finetuned from model:** unsloth/Qwen3-1.7B
+<!-- Provide a longer summary of what this model is. -->
+
+
 
-This adapter is designed to help the base model make balanced decisions in a simulated kingdom management scenario, using prompts that describe the current state of the kingdom and possible actions.
+- **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://huggingface.co/Slyracoon23/dynastai-grpo-lora
+<!-- 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
 
-- Plug this LoRA adapter into the Qwen3-1.7B base model to act as a decision-making advisor for the DynastAI kingdom simulation game.
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
 
-### Downstream Use
+### Downstream Use [optional]
 
-- Can be used as a component in larger simulation or game AI systems where balanced decision-making is required.
+<!-- 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
 
-- Not intended for real-world policy or governance decisions.
-- Not suitable for use outside the context of the DynastAI simulation or similar games.
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
 
 ## Bias, Risks, and Limitations
 
-- The model is trained on synthetic game data and may not generalize to real-world scenarios.
-- Decisions are optimized for game balance, not for ethical or real-world outcomes.
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
 
 ### Recommendations
 
-Users should be aware that this model is for entertainment and research purposes only.
+<!-- 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
 
-```python
-from peft import PeftModel, PeftConfig
-from transformers import AutoModelForCausalLM, AutoTokenizer
+Use the code below to get started with the model.
 
-base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-1.7B")
-tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B")
-peft_model = PeftModel.from_pretrained(base_model, "Slyracoon23/dynastai-grpo-lora")
-```
+[More Information Needed]
 
 ## Training Details
 
 ### Training Data
 
-- Synthetic prompts and solutions generated from the DynastAI kingdom simulation game, focusing on balancing four metrics: Church, People, Military, Treasury.
+<!-- 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
 
-- Fine-tuned using GRPO (Generative Reward-based Policy Optimization) with custom reward functions to encourage brevity and correctness.
+<!-- 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
 
-- **Batch size:** 4
-- **Epochs:** 3
-- **Learning rate:** 2e-4
-- **Optimizer:** AdamW (8-bit)
-- **Precision:** 16-bit (LoRA)
+- **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
 
-- Evaluated on a held-out set of synthetic prompts for accuracy in selecting the optimal choice.
+<!-- 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:** 2 × NVIDIA L4 GPUs (each with 23 GB VRAM), Intel(R) Xeon(R) CPU @ 2.20GHz (24 vCPUs)
-- **Storage:** 500 GB NVMe SSD
-- **Operating System:** Ubuntu 24.04.2 LTS
-- **Cloud Provider:** Google Cloud Platform (GCP)
-- **Compute Region:** northamerica-northeast2 (from hostname: nvidia-l4-double-gpu-northamerica-northeast2-b)
-- **Hours used:** 5.8hrs
+- **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
 
-## Technical Specifications
+[More Information Needed]
 
-- **Base Model:** Qwen3-1.7B
-- **Adapter Type:** LoRA
-- **Framework:** PEFT 0.15.2
+#### Hardware
 
-## Citation
+[More Information Needed]
 
-If you use this model, please cite the base model and this repository.
+#### Software
 
-## Model Card Authors
+[More Information Needed]
 
-- Slyracoon23
+## 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
 
-- [Your contact info or Hugging Face profile]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "gate_proj",
-    "o_proj",
-    "down_proj",
+    "k_proj",
     "up_proj",
-    "v_proj"
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd658abe5258db738c7217a299b1ff1f6aec8050776d1523bc6188de228c598
+oid sha256:2578cac168a04c524ae1da1e7f422c51cf8baedec007ed15f4e8c581da95c78b
 size 34917504