Instructions to use User01110/testing-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use User01110/testing-2 with Transformers:

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

pipe = pipeline("text-generation", model="User01110/testing-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("User01110/testing-2")
model = AutoModelForCausalLM.from_pretrained("User01110/testing-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 User01110/testing-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "User01110/testing-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": "User01110/testing-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/User01110/testing-2

SGLang

How to use User01110/testing-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 "User01110/testing-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": "User01110/testing-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 "User01110/testing-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": "User01110/testing-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use User01110/testing-2 with Docker Model Runner:
```
docker model run hf.co/User01110/testing-2
```

testing-2

This is an experimental ChatML SFT run from SupraLabs/Supra-1.5-50M-Base-exp.

Training Setup

Field	Value
Base model	`SupraLabs/Supra-1.5-50M-Base-exp`
Output repo	`User01110/testing-2`
Sequence length	1024
Max optimizer steps	10,000
Per-device batch size	128
Gradient accumulation	4
Sample presentations per GPU	5,120,000
Max token slots per GPU	5,242,880,000
Learning rate	2.00e-04
Warmup steps	100
Weight decay	0.05
Save/push cadence	every 1,000 optimizer steps plus final
Loss mask	all assistant spans only
Chat format	ChatML
System prompt	`You are a helpful assistant.`

The stream reloops datasets as needed to reach the fixed step budget. Cutecat6152/python-data-basic is capped at three passes because it only has 100 rows.

Unique one-pass source rows listed below: 4,128,528. First-cycle source presentations with the python-data-basic cap included: 4,128,728. The 10,000-step training budget presents 5,120,000 examples per GPU, so larger sources are expected to reloop during training.

ChatML Compatibility

The tokenizer is saved with:

Token	Purpose
`<	im_start
`<	im_end

The uploaded tokenizer includes the ChatML template, so inference and future SFT should not require manually adding these tokens again.

Example prompt:

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain what a neural network is in simple terms."},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

Dataset Mix

Dataset	Config	Split	Rows	Schema	Mapping	Pass policy
nvidia/Nemotron-SFT-Instruction-Following-Chat-v2	default	reasoning_off	1,068,273	messages[{role, content, reasoning_content}]	user/assistant message pairs; reasoning_off only	reloops as needed
microsoft/orca-math-word-problems-200k	default	train	200,035	question, answer	user=question; assistant=answer	reloops as needed
TIGER-Lab/MathInstruct	default	train	262,039	instruction, output	user=instruction; assistant=output	reloops as needed
Programming-Language/codeagent-python	default	train	296,837	prompt, response	user=prompt; assistant=response	reloops as needed
Cutecat6152/python-data-basic	default	train	100	id, instruction, response	user=instruction; assistant=response	max 3 passes, 300 presentations max
flytech/python-codes-25k	default	train	49,626	instruction, input, output, text	user=instruction plus optional Input block; assistant=output	reloops as needed
QuixiAI/open-instruct-uncensored	default	train	1,756,115	dataset, id, messages[{role, content}]	user/assistant message pairs	reloops as needed
User01110/multiturn-instruct	default	train	2,732	messages[{role, content}], token_count, session metadata	full multi-turn ChatML; labels only on assistant spans	reloops as needed
Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned	4 configs: General-Distillation, General-Math, MultilingualSTEM, PHD-Science	train	457,825	id, conversations[{from, value}], input, output, domain, meta	user=input; assistant=output after removing ... blocks	reloops as needed
openai/gsm8k	main	train	7,473	question, answer	user=question; assistant=answer	reloops as needed
openai/gsm8k	socratic	train	7,473	question, answer	user=question; assistant=answer	reloops as needed
EleutherAI/arithmetic	10 selected subsets	validation raw JSONL	20,000	context, completion	user=context with trailing Answer: stripped; assistant=completion	reloops as needed

Notes

Dataset schemas and row counts were checked through Hugging Face Dataset Viewer metadata where available.
Nemotron is loaded from the direct reasoning_off.jsonl file to avoid mixing in reasoning-on schema fields.
EleutherAI arithmetic is loaded from raw JSONL files to avoid old dataset-script loading issues.
Kimi K2.5 cleaned reasoning rows are loaded from all four train configs. Assistant <think>...</think> blocks are stripped before ChatML rendering, so hidden reasoning is not included in the completion-only loss.
Streaming source open/read failures are retried and reopened before a source is dropped, which protects long cloud runs from transient Hub DNS/client errors.
RoPE buffers and tokenizer/model load are verified during final export.

Downloads last month: -

Safetensors

Model size

51.8M params

Tensor type

F32

Model tree for User01110/testing-2

Base model

SupraLabs/Supra-1.5-50M-Base-exp

Finetuned

(6)

this model