Downloads · 30 days
9
28% of all-time downloads
Qwen-1.5B-instruct-frozenlake
CuriousDragon/Qwen-1.5B-instruct-frozenlake
Qwen-1.5B-instruct-frozenlake is a machine learning model from CuriousDragon. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is fine-tuned on the FrozenLake-v1 environment to find optimal paths while avoiding holes.
All-time downloads
32
Public
Parameters
1.5B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Feb 24, 2025
- Updated
- Feb 25, 2025
- SHA
- 261542fa
Model card
From the Hugging Face model README
FrozenLake Solver - Merged Qwen Model
This model is fine-tuned on the FrozenLake-v1 environment to find optimal paths while avoiding holes.
Model Details
- Base Model: Qwen/Qwen2.5-1.5B-Instruct
- Training Method: LoRA fine-tuning + Merge
- Task: Path Planning in FrozenLake Environment
Performance Metrics
- Path Accuracy: 20.00%
- Action Accuracy: 0.00%
- Test Samples: 5
Usage Example
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CuriousDragon/Qwen-1.5B-instruct-frozenlake")
tokenizer = AutoTokenizer.from_pretrained("CuriousDragon/Qwen-1.5B-instruct-frozenlake")
- Type
- qwen2
- Created
- Feb 24, 2025
- Updated
- Feb 25, 2025