Image-Text-to-Text
PEFT
Safetensors
openenv
trl
grpo
reinforcement-learning
lora
visual-geolocation
geoguessr
conversational
Eval Results (legacy)
Instructions to use FineEnvs/geoguesser-qwen3.5-4b-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use FineEnvs/geoguesser-qwen3.5-4b-grpo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "FineEnvs/geoguesser-qwen3.5-4b-grpo") - Notebooks
- Google Colab
- Kaggle
Card: FineEnvs citation
Browse files
README.md
CHANGED
|
@@ -116,3 +116,14 @@ vllm serve Qwen/Qwen3.5-4B --enable-lora \
|
|
| 116 |
- **[Code and exact commands](https://github.com/adithya-s-k/HuggingEnvs/tree/main/03-geoguesser)**
|
| 117 |
|
| 118 |
Imagery is Mapillary, CC BY-SA 4.0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
- **[Code and exact commands](https://github.com/adithya-s-k/HuggingEnvs/tree/main/03-geoguesser)**
|
| 117 |
|
| 118 |
Imagery is Mapillary, CC BY-SA 4.0.
|
| 119 |
+
|
| 120 |
+
## Citation
|
| 121 |
+
|
| 122 |
+
```bibtex
|
| 123 |
+
@misc{fineenvs,
|
| 124 |
+
author = {Kolavi, Adithya S},
|
| 125 |
+
title = {FineEnvs: Open Source RL Environments for LLM Agents},
|
| 126 |
+
year = {2026},
|
| 127 |
+
url = {https://github.com/adithya-s-k/FineEnvs}
|
| 128 |
+
}
|
| 129 |
+
```
|