Instructions to use FlippyDora/qwen_sft_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlippyDora/qwen_sft_2 with Transformers:

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

pipe = pipeline("text-generation", model="FlippyDora/qwen_sft_2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlippyDora/qwen_sft_2")
model = AutoModelForCausalLM.from_pretrained("FlippyDora/qwen_sft_2")
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 FlippyDora/qwen_sft_2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlippyDora/qwen_sft_2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlippyDora/qwen_sft_2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlippyDora/qwen_sft_2

SGLang

How to use FlippyDora/qwen_sft_2 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 "FlippyDora/qwen_sft_2" \
    --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": "FlippyDora/qwen_sft_2",
		"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 "FlippyDora/qwen_sft_2" \
        --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": "FlippyDora/qwen_sft_2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlippyDora/qwen_sft_2 with Docker Model Runner:
```
docker model run hf.co/FlippyDora/qwen_sft_2
```

See axolotl config

axolotl version: 0.8.0.dev0

base_model: outputs/qwen_sft_1
trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: qwen_25
datasets:
  - path: data/data_2/train_data
    type: chat_template
    field_messages: conversations
    message_field_role: role
    message_field_content: content
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant", "ai"]
      system: ["system"]

dataset_prepared_path:
val_set_size: 0.0
output_dir: ./outputs/qwen_sft_2

sequence_len: 8192
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

# wandb_project: huggingface
# wandb_entity: zzzzzaa
# wandb_watch:
# wandb_name: qwen_test
# wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 1e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16: false
tf32: true

gradient_checkpointing: false
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.05
saves_per_epoch: 1
evals_per_epoch: 0
debug:
weight_decay: 0.01
fsdp:
fsdp_config:
# special_tokens:
#   bos_token: "<|im_start|>"
#   eos_token: "<|im_end|>"
#   pad_token: "<|endoftext|>"


plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
liger_fused_linear_cross_entropy: true

outputs/qwen_sft_2

This model was trained from scratch on the None 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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 1.0

Training results

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16