Instructions to use adityabanerjee13/qwen2.5-0.5b-sft-IT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adityabanerjee13/qwen2.5-0.5b-sft-IT with Transformers:

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

pipe = pipeline("text-generation", model="adityabanerjee13/qwen2.5-0.5b-sft-IT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adityabanerjee13/qwen2.5-0.5b-sft-IT")
model = AutoModelForCausalLM.from_pretrained("adityabanerjee13/qwen2.5-0.5b-sft-IT", 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 adityabanerjee13/qwen2.5-0.5b-sft-IT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adityabanerjee13/qwen2.5-0.5b-sft-IT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adityabanerjee13/qwen2.5-0.5b-sft-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adityabanerjee13/qwen2.5-0.5b-sft-IT

SGLang

How to use adityabanerjee13/qwen2.5-0.5b-sft-IT 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 "adityabanerjee13/qwen2.5-0.5b-sft-IT" \
    --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": "adityabanerjee13/qwen2.5-0.5b-sft-IT",
		"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 "adityabanerjee13/qwen2.5-0.5b-sft-IT" \
        --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": "adityabanerjee13/qwen2.5-0.5b-sft-IT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adityabanerjee13/qwen2.5-0.5b-sft-IT with Docker Model Runner:
```
docker model run hf.co/adityabanerjee13/qwen2.5-0.5b-sft-IT
```

See axolotl config

axolotl version: 0.19.0.dev0

# ==============================================================================
# Axolotl CPT config — Qwen2.5-0.5B, full-parameter, single GPU.
# Data mix RATIO EXPERIMENT (character-level exact):
#
#   RUN 2 of 3 — fineweb : indic = 1 : 2   (FineWeb is HALF the Indic size)
#   FineWeb web-crawl chars == Indic train chars / 2.
#
# Indic train  : adityabanerjee13/indic-cpt-mini-train   (7,907,882 chars)
# FineWeb train: adityabanerjee13/fineweb-cpt-half       (3,953,941 chars)
# Validation   : adityabanerjee13/indic-cpt-mini-val     (held-out 1% Indic)
#
# The datasets are pre-sized to exact character counts on the Hub, so loading
# each one whole gives the exact 1:2 ratio — no slicing needed.
#
# Usage:
#   python train.py --config qwen2.5_0.5b_cpt_mix_1to2.yml
# ==============================================================================

base_model: adityabanerjee13/qwen2.5-0.5b-cpt-mix-1to2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: false

adapter:
load_in_8bit: false
load_in_4bit: false

# multi_eval_plugin splits test_datasets back into per-source eval sets so
# this run logs eval_indic_cpt_mini_val_loss and eval_fineweb_cpt_val_loss
# separately (instead of one merged eval_loss) at every eval step, incl. to
# wandb. Requires this folder on PYTHONPATH — launch via
# `python train.py --config <this file>`.
plugins:
  - multi_eval_plugin.MultiEvalPlugin

datasets:
  - path: adityabanerjee13/indic-sft-mini-train
    type: chat_template
    field_messages: messages
    split: train
  - path: adityabanerjee13/tulu-sft-mini-train
    type: chat_template
    field_messages: messages
    split: train

test_datasets:
  - path: adityabanerjee13/indic-sft-mini-val
    type: chat_template
    field_messages: messages
    split: validation
  - path: adityabanerjee13/tulu-sft-mini-val
    type: chat_template
    field_messages: messages
    split: validation

train_on_inputs: false   

chat_template: tokenizer_default

dataset_prepared_path: ./last_run_prepared_1to2
dataset_num_proc: 1          # single-process tokenize: avoids fork deadlock
val_set_size: 0
output_dir: ./outputs/qwen2.5-0.5b-sft-IT

# --- Sequence packing -----------------------------------------------------
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

# --- Optimization ----------------------------------------------------------
gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5
warmup_ratio: 0.03
weight_decay: 0.01
max_grad_norm: 1.0

train_on_inputs: true
group_by_length: false

# --- Precision / memory ---------------------------------------------------
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
flash_attention: true

# --- Logging / checkpoints ------------------------------------------------
logging_steps: 10
save_strategy: steps
save_steps: 500
save_total_limit: 30
save_only_model: true   # save weights only — no optimizer/scheduler state
                        # (checkpoints ~1/3 the size; can't resume training)
evals_per_epoch: 4

wandb_project: indic-sft
wandb_entity: models-na9841
wandb_name: qwen2.5-0.5b-sft-IT
wandb_log_model: "false"

hub_model_id: adityabanerjee13/qwen2.5-0.5b-sft-IT
hub_strategy: all_checkpoints

special_tokens:

qwen2.5-0.5b-sft-IT

This model is a fine-tuned version of adityabanerjee13/qwen2.5-0.5b-cpt-mix-1to2 on the adityabanerjee13/indic-sft-mini-train and the adityabanerjee13/tulu-sft-mini-train datasets.

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 17
training_steps: 591

Training results

Framework versions

Transformers 5.14.1
Pytorch 2.12.0+cu130
Datasets 4.8.4
Tokenizers 0.22.2

Downloads last month: 248

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for adityabanerjee13/qwen2.5-0.5b-sft-IT

Base model

Qwen/Qwen2.5-0.5B

Finetuned

adityabanerjee13/qwen2.5-0.5b-cpt-mix-1to2

Finetuned

(2)

this model

Finetunes

2 models

adityabanerjee13
/

qwen2.5-0.5b-sft-IT

qwen2.5-0.5b-sft-IT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for adityabanerjee13/qwen2.5-0.5b-sft-IT

Datasets used to train adityabanerjee13/qwen2.5-0.5b-sft-IT