Instructions to use dbaysal/qwen2.5coder-3b-learned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbaysal/qwen2.5coder-3b-learned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B")
model = PeftModel.from_pretrained(base_model, "dbaysal/qwen2.5coder-3b-learned")

Transformers

How to use dbaysal/qwen2.5coder-3b-learned with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dbaysal/qwen2.5coder-3b-learned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbaysal/qwen2.5coder-3b-learned")
model = AutoModelForCausalLM.from_pretrained("dbaysal/qwen2.5coder-3b-learned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dbaysal/qwen2.5coder-3b-learned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbaysal/qwen2.5coder-3b-learned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbaysal/qwen2.5coder-3b-learned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dbaysal/qwen2.5coder-3b-learned

SGLang

How to use dbaysal/qwen2.5coder-3b-learned with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dbaysal/qwen2.5coder-3b-learned" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbaysal/qwen2.5coder-3b-learned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dbaysal/qwen2.5coder-3b-learned" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbaysal/qwen2.5coder-3b-learned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dbaysal/qwen2.5coder-3b-learned with Docker Model Runner:
```
docker model run hf.co/dbaysal/qwen2.5coder-3b-learned
```

qwen2.5coder-3b-learned / README.md

dbaysal

Upload LoRA adapter checkpoints

cb08a2f verified 21 days ago

preview code

Raw

History Blame Contribute Delete

4.07 kB

	---
	library_name: peft
	license: other
	base_model: Qwen/Qwen2.5-Coder-3B
	tags:
	- axolotl
	- base_model:adapter:Qwen/Qwen2.5-Coder-3B
	- lora
	- transformers
	datasets:
	- dbaysal/all-contentx3
	pipeline_tag: text-generation
	model-index:
	- name: out/learned
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
	<details><summary>See axolotl config</summary>

	axolotl version: `0.17.0`
	```yaml
	# Axolotl config - LEARNED model (base fine-tuned on the full benchmark corpus:
	# forget targets + retained neighbors + controls). This is the "before unlearning" state.
	#
	# Option A: our JSONL stays as {"prompt": ..., "completion": ...}. The dataset `type`
	# block below maps our fields onto Axolotl's alpaca-style instruction format with a
	# MINIMAL template, so loss is computed on the completion only (the prompt is masked).
	# No data rewrite needed.
	#
	# Run: axolotl train benchmark/training/axolotl_learned.yaml

	base_model: Qwen/Qwen2.5-Coder-3B # swap for your base/code model; a NON-chat base
	# model is preferred (no chat template to confound
	# what gets memorized). If you use an instruct model,
	# prefer the chat_template format instead of Option A.
	strict: false

	# --- data: map {prompt, completion} -> instruction/output, minimal template -----------------
	datasets:
	- path: dbaysal/all-contentx3
	type: completion
	field: content

	dataset_prepared_path: ./out/prepared_full
	val_set_size: 0.0 # tiny corpus; don't carve out a val split
	output_dir: ./out/learned

	# --- sequence / packing ---------------------------------------------------------------------
	sequence_len: 2048
	sample_packing: false # IMPORTANT: keep one example per sequence so each
	# item is memorized cleanly (packing concatenates rows)
	pad_to_sequence_len: true

	# --- LoRA (matches the design doc's "short LoRA fine-tunes"; set adapter: to ''/full for full FT)
	adapter: lora
	lora_r: 64
	lora_alpha: 128
	lora_dropout: 0.05
	lora_target_linear: true

	# --- optimization (TOFU reference: ~5 epochs, LR 1e-5 on a 7B model) ------------------------
	num_epochs: 5 # bump (or use sft_full_repeat5.jsonl) until the
	# memorization-yield gate clears its threshold
	micro_batch_size: 8
	gradient_accumulation_steps: 4
	optimizer: adamw_torch
	lr_scheduler: cosine
	learning_rate: 2.0e-4
	warmup_ratio: 0.03
	weight_decay: 0.0

	bf16: auto
	tf32: false

	gradient_checkpointing: true
	flash_attention: true
	logging_steps: 1
	seed: 42 # vary across >=3 seeds for the final runs

	```

	</details><br>

	# out/learned

	This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B](https://huggingface.co/Qwen/Qwen2.5-Coder-3B) on the dbaysal/all-contentx3 dataset.

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.0002
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- gradient_accumulation_steps: 4
	- total_train_batch_size: 32
	- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 8
	- training_steps: 282

	### Training results



	### Framework versions

	- PEFT 0.19.1
	- Transformers 5.9.0
	- Pytorch 2.11.0+cu128
	- Datasets 4.8.5
	- Tokenizers 0.22.2