Instructions to use AlexHung29629/MyModel2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexHung29629/MyModel2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="AlexHung29629/MyModel2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("AlexHung29629/MyModel2")
model = AutoModelForMultimodalLM.from_pretrained("AlexHung29629/MyModel2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlexHung29629/MyModel2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexHung29629/MyModel2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexHung29629/MyModel2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AlexHung29629/MyModel2

SGLang

How to use AlexHung29629/MyModel2 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 "AlexHung29629/MyModel2" \
    --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": "AlexHung29629/MyModel2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "AlexHung29629/MyModel2" \
        --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": "AlexHung29629/MyModel2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use AlexHung29629/MyModel2 with Docker Model Runner:
```
docker model run hf.co/AlexHung29629/MyModel2
```

MyModel2 / README.md

AlexHung29629

Upload folder using huggingface_hub

587aeeb verified 6 days ago

preview code

Raw History Blame Contribute Delete

5.19 kB

metadata

library_name: transformers
base_model: google/gemma-4-26B-A4B-it
tags:
  - generated_from_trainer
datasets:
  - data/ultradata-sft.jsonl
  - data/ultradata-sft-agent.jsonl
  - data/tw-sft.jsonl
model-index:
  - name: outputs/gemma4-26b-fft
    results: []

See axolotl config

axolotl version: 0.19.0.dev0

# 4 節點 × 8 張 H100，全參數 FSDP2。由 train.sbatch 送出。
# 不要在登入節點跑 preprocess 或 train。
# global batch = 32 * micro_batch_size * gradient_accumulation_steps。
base_model: google/gemma-4-26B-A4B-it

# Gemma 4 權重是 Gemma4ForConditionalGeneration，不要強制 AutoModelForCausalLM。
# 這次是文字 SFT，凍結 vision / audio tower。
freeze_mm_modules: true

plugins:
  - axolotl.integrations.liger.LigerPlugin

liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
# multimodal Gemma 4 的 liger 沒有 fused linear CE。
liger_fused_linear_cross_entropy: false
# EAFT 自帶 fused lm_head+loss，不能跟 CCE 同時開。
cut_cross_entropy: false

# 容器內建的 EAFT kernel。這四個鍵要一起開。
use_eaft: true
eaft_alpha: 0.333
eaft_k: 20
eaft_normalize: true

# 全參數。不要加 adapter、4bit、quantize_moe_experts。
load_in_8bit: false
load_in_4bit: false

datasets:
  - path: data/ultradata-sft.jsonl
    type: input_output
  - path: data/ultradata-sft-agent.jsonl
    type: input_output
  - path: data/tw-sft.jsonl
    type: input_output

dataset_prepared_path: ./prepared/gemma4-26b-fft-65536
output_dir: ./outputs/gemma4-26b-fft
dataset_num_proc: 64
train_on_inputs: false
val_set_size: 0
seed: 42

# 使用者指定 65536、gradient_accumulation_steps 1。
# 8 卡 smoke 這個長度、accum 1 過了（峰值 71.45GiB）。
# 32 卡 accum 2 時 backward 還要 5.50GiB，當時只剩約 4.5GiB。
# 超過這個長度的樣本，Axolotl preprocess 會丟掉。
sequence_len: 65536
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

use_tensorboard: true

# 32 張 H100。global batch = 32 * 1 * 1 * 65536 = 2,097,152 tokens。
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2

optimizer: adamw_torch_fused
learning_rate: 5.0e-6
lr_scheduler: cosine
warmup_ratio: 0.03
weight_decay: 0.01
max_grad_norm: 1.0

bf16: auto
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
# 183274 打開後，backward 仍是已佔 72.23GiB 再要 5.50GiB。這段 workspace 沒被 offload 移走。
activation_offloading: false

# FSDP2 把參數、梯度、optimizer state 切到 32 張卡。
# 必須包文字 decoder。不指定時 FSDP 會去找不存在的 Gemma4AudioLayer。
# 存檔用 FULL_STATE_DICT，集中成一份權重。不寫 optimizer state，不能從 optimizer 續訓。
fsdp_version: 2
fsdp_config:
  offload_params: false
  cpu_ram_efficient_loading: true
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Gemma4TextDecoderLayer
  state_dict_type: FULL_STATE_DICT
  reshard_after_forward: true

# flex attention。全域層 head_dim=512，FA2 單獨跑不了。
# 參數照 MEGA/train.yml。H100 預設 flex 會 SRAM OOM。
attn_implementation: flex_attention
flex_attn_kernel_options:
  num_stages: 1
  bwd_num_stages: 1

logging_steps: 1
saves_per_epoch: 1
save_total_limit: 2
# 只存模型參數。optimizer、scheduler、rng 都不寫進 checkpoint。
save_only_model: true

special_tokens:
  bos_token: "<bos>"
  eos_token: "<eos>"
  pad_token: "<pad>"
  unk_token: "<unk>"

# preprocess --debug 若把要學的 <turn|> 標成 -100，拿掉這段。
eot_tokens:
  - "<turn|>"

outputs/gemma4-26b-fft

This model is a fine-tuned version of google/gemma-4-26B-A4B-it on the data/ultradata-sft.jsonl, the data/ultradata-sft-agent.jsonl and the data/tw-sft.jsonl 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: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 32
total_eval_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: 21
training_steps: 722

Training results

Framework versions

Transformers 5.14.1
Pytorch 2.11.0+cu130
Datasets 4.8.4
Tokenizers 0.22.2