Instructions to use timarni/base_test_set with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timarni/base_test_set with Transformers:

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

pipe = pipeline("text-generation", model="timarni/base_test_set")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("timarni/base_test_set")
model = AutoModelForCausalLM.from_pretrained("timarni/base_test_set", device_map="auto")
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 timarni/base_test_set with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/timarni/base_test_set

SGLang

How to use timarni/base_test_set 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 "timarni/base_test_set" \
    --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": "timarni/base_test_set",
		"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 "timarni/base_test_set" \
        --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": "timarni/base_test_set",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use timarni/base_test_set with Docker Model Runner:
```
docker model run hf.co/timarni/base_test_set
```

base_test_set / README.md

timarni

Upload final fine-tuned Qwen3-0.6B model

182d8ba verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

3.38 kB

metadata

library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B-Base
tags:
  - generated_from_trainer
datasets:
  - timarni/MNLP_M2_mcqa_dataset
model-index:
  - name: outputs/base_test_set
    results: []

See axolotl config

axolotl version: 0.9.2

base_model: Qwen/Qwen3-0.6B-Base
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false

chat_template: qwen3
datasets:
  - path: timarni/MNLP_M2_mcqa_dataset
    type: alpaca
    split: train

shuffle_merged_datasets: true

val_set_size: 0.1
output_dir: ./outputs/base_test_set
dataset_prepared_path: last_run_prepared

sequence_len: 4096 #2048
sample_packing: true # was true -> need to check if it actually learns on the samples or not (better understand te hyperparam and event. install axolotl to debug)
eval_sample_packing: false
pad_to_sequence_len: true
# train_on_inputs: true # NEW
# group_by_length: false NEW?

# To be sure that no LORA is done
adapter: null
lora: false
merge_lora: false

wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: base_test_set
wandb_log_model:

gradient_accumulation_steps: 16 # 2
micro_batch_size: 2 # 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005 # 0.00005
# cosine_min_lr_ratio: 0.1

warmup_ratio: 0.05
weight_decay: 0.01

bf16: auto
tf32: true

gradient_checkpointing: offload
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
gradient_clipping: 1.0 # or max_grad_norm?
flash_attention: true

evals_per_epoch: 4
saves_per_epoch: 2
save_total_limit: 20
special_tokens:

outputs/base_test_set

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on the timarni/MNLP_M2_mcqa_dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.1689

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: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4926	0.6957	1	0.2934
0.197	1.0	2	0.1959
0.127	1.6957	3	0.1689

Framework versions

Transformers 4.51.3
Pytorch 2.5.1+cu121
Datasets 3.5.1
Tokenizers 0.21.1