Instructions to use WokeAI/Tankie-7b_1bA-sft-warmup-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WokeAI/Tankie-7b_1bA-sft-warmup-v0 with Transformers:

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

pipe = pipeline("text-generation", model="WokeAI/Tankie-7b_1bA-sft-warmup-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("WokeAI/Tankie-7b_1bA-sft-warmup-v0")
model = AutoModelForMultimodalLM.from_pretrained("WokeAI/Tankie-7b_1bA-sft-warmup-v0")
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 WokeAI/Tankie-7b_1bA-sft-warmup-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WokeAI/Tankie-7b_1bA-sft-warmup-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WokeAI/Tankie-7b_1bA-sft-warmup-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WokeAI/Tankie-7b_1bA-sft-warmup-v0

SGLang

How to use WokeAI/Tankie-7b_1bA-sft-warmup-v0 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 "WokeAI/Tankie-7b_1bA-sft-warmup-v0" \
    --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": "WokeAI/Tankie-7b_1bA-sft-warmup-v0",
		"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 "WokeAI/Tankie-7b_1bA-sft-warmup-v0" \
        --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": "WokeAI/Tankie-7b_1bA-sft-warmup-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WokeAI/Tankie-7b_1bA-sft-warmup-v0 with Docker Model Runner:
```
docker model run hf.co/WokeAI/Tankie-7b_1bA-sft-warmup-v0
```

Tankie-7b_1bA-sft-warmup-v0 / README.md

Fizzarolli

Upload folder using huggingface_hub

5388d72 verified 8 months ago

preview code

raw

history blame contribute delete

3.15 kB

metadata

library_name: transformers
license: apache-2.0
base_model: ibm-granite/granite-4.0-h-tiny
tags:
  - generated_from_trainer
datasets:
  - WokeAI/polititune-tankie-warmup
model-index:
  - name: model-output
    results: []

See axolotl config

axolotl version: 0.13.0.dev0

# === Model Configuration ===
base_model: ibm-granite/granite-4.0-h-tiny
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 2
micro_batch_size: 1
gradient_accumulation_steps: 1
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

# === Hyperparameter Configuration ===
optimizer: adamw_torch_8bit
learning_rate: 1e-5
lr_scheduler: constant
weight_decay: 0.01
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

# === Data Configuration ===
datasets:
  - path: WokeAI/polititune-tankie-warmup
    type: chat_template
    split: train
chat_template: tokenizer_default

dataset_prepared_path: last_run_prepared

# === Hardware Optimization ===
gradient_checkpointing: offload

# === Wandb Tracking ===
wandb_project: polititune-q34b-warmup

# === Checkpointing ===
saves_per_epoch: 2

# === Advanced Settings ===
output_dir: ./model-output
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: true




fsdp:
  - auto_wrap
  - full_shard
fsdp_config:
  fsdp_version: 2
  fsdp_offload_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: GraniteMoeHybridDecoderLayer
  fsdp_state_dict_type: SHARDED_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_reshard_after_forward: true
  fsdp_activation_checkpointing: true # will disable if doesnt work

model-output

This model is a fine-tuned version of ibm-granite/granite-4.0-h-tiny on the WokeAI/polititune-tankie-warmup 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
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 3
training_steps: 78

Training results

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.22.1