Downloads · 30 days
0
eagle0504/fine-tuned-DeepSeek-R1-Distill-Qwen-1.5B-openai-gsm8k-enhanced-v1
fine-tuned-DeepSeek-R1-Distill-Qwen-1.5B-openai-gsm8k-enhanced-v1 is a machine learning model from eagle0504. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B using the LoRA (Low-Rank Adaptation) method to adapt the base model on an enhanced version of the GSM8K dataset. The model is designed fo…
Downloads · 30 days
0
Access
Public
Updated Mar 23, 2025
Repo size
15.8 MB
Likes
0
Public
Click a slice to open those files.
.json11.4 MB · 72%
From the Hugging Face model README
Model IDThis model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B using the LoRA (Low-Rank Adaptation) method to adapt the base model on an enhanced version of the GSM8K dataset. The model is designed for English language causal language modeling tasks with a focus on math word problem solving.
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bq_proj and v_proj layers for efficient fine-tuning.TaskType.CAUSAL_LM) on math reasoning problems.eagle0504/openai-gsm8k-enhanced-using-together-ai-deepseek-train8k-test1k-v1This model was fine-tuned using the transformers and peft libraries. The training leveraged the Parameter-Efficient Fine-Tuning (PEFT) technique using LoRA for memory efficiency and faster convergence.
from peft import get_peft_model, LoraConfig, TaskType
lora_config = LoraConfig(
task_type=TaskType.CAUSAL_LM,
r=8,
lora_alpha=16,
target_modules=["q_proj", "v_proj"],
lora_dropout=0.1,
bias="none",
)
model = get_peft_model(model, lora_config)
r=8: Low-rank dimensionalitylora_alpha=16: Scaling factorlora_dropout=0.1: Regularizationtarget_modules=["q_proj", "v_proj"]: Applies LoRA to attention layersbias="none": No bias added to adapted layersfrom transformers import TrainingArguments
training_args = TrainingArguments(
per_device_train_batch_size=1,
gradient_accumulation_steps=8,
warmup_steps=100,
num_train_epochs=3,
learning_rate=2e-4,
fp16=True,
logging_steps=10,
output_dir="outputs",
report_to="none",
remove_unused_columns=False,
)
1 × 8 = 8 (via gradient accumulation)fp16=True) for speed and efficiencyThis model is intended for educational and research purposes in math word problem solving, reasoning tasks, and language modeling. It can be used as-is or further fine-tuned on domain-specific datasets.
This model is released under the MIT License.
While the base model and fine-tuning procedure are robust, this model inherits limitations from both the original dataset (GSM8K) and the DeepSeek architecture, including potential biases in language and reasoning patterns. Caution is advised when using the model in high-stakes or real-world applications.