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

Libraries

How to use satpalsr/testkaro with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("satpalsr/testkaro")
model = AutoModelForCausalLM.from_pretrained("satpalsr/testkaro")
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

vLLM

How to use satpalsr/testkaro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/satpalsr/testkaro

SGLang

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

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

See axolotl config

axolotl version: 0.12.0

# the original mxfp4 quantized model is not supported with FSDP cpu_ram_efficient_loading
# FSDP cpu_ram_efficient_loading is used to reduce the initial CPU memory usage when loading the model
base_model: axolotl-ai-co/gpt-oss-20b-dequantized

use_kernels: false

dp_shard_size: 8  # requires 2x8xH100 nodes

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

experimental_skip_move_to_device: true  # prevent OOM by NOT putting model to GPU before sharding

datasets:
  - path: HuggingFaceH4/Multilingual-Thinking
    type: chat_template
    field_thinking: thinking
    template_thinking_key: thinking

dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/gpt-oss-20b/
#save_only_model: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: gpt-oss-20b
wandb_name: fft-20b

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 1

optimizer: adamw_torch_fused  # 8bit optimizers do not work with FSDP2 offload
lr_scheduler: constant_with_warmup
learning_rate: 2e-5
load_best_model_at_end: false

bf16: true
tf32: true

flash_attention: true
attn_implementation: kernels-community/vllm-flash-attn3

gradient_checkpointing: true
activation_offloading: true

logging_steps: 1
saves_per_epoch: 1

warmup_ratio: 0.03

special_tokens:
eot_tokens:
  - "<|end|>"

#deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
fsdp_version: 2
fsdp_config:
  offload_params: true
  state_dict_type: SHARDED_STATE_DICT
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: GptOssDecoderLayer
  reshard_after_forward: true
  cpu_ram_efficient_loading: true

outputs/gpt-oss-20b/

This model is a fine-tuned version of axolotl-ai-co/gpt-oss-20b-dequantized on the HuggingFaceH4/Multilingual-Thinking 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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
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: constant_with_warmup
training_steps: 8

Training results

Framework versions

Transformers 4.55.0
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 3

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for satpalsr/testkaro

Base model

axolotl-ai-co/gpt-oss-20b-dequantized

Finetuned

(3)

this model

Duplicated from ZeroAgency/gpt-oss-20b-multilingual-reasoning

satpalsr
/

testkaro

outputs/gpt-oss-20b/

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for satpalsr/testkaro

Dataset used to train satpalsr/testkaro