Instructions to use laion/tt-x10-fsdp2-fa2-117-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/tt-x10-fsdp2-fa2-117-30B with Transformers:

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

pipe = pipeline("text-generation", model="laion/tt-x10-fsdp2-fa2-117-30B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/tt-x10-fsdp2-fa2-117-30B")
model = AutoModelForCausalLM.from_pretrained("laion/tt-x10-fsdp2-fa2-117-30B", device_map="auto")
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 laion/tt-x10-fsdp2-fa2-117-30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/tt-x10-fsdp2-fa2-117-30B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/tt-x10-fsdp2-fa2-117-30B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/tt-x10-fsdp2-fa2-117-30B

SGLang

How to use laion/tt-x10-fsdp2-fa2-117-30B 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 "laion/tt-x10-fsdp2-fa2-117-30B" \
    --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": "laion/tt-x10-fsdp2-fa2-117-30B",
		"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 "laion/tt-x10-fsdp2-fa2-117-30B" \
        --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": "laion/tt-x10-fsdp2-fa2-117-30B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/tt-x10-fsdp2-fa2-117-30B with Docker Model Runner:
```
docker model run hf.co/laion/tt-x10-fsdp2-fa2-117-30B
```

tt-x10-fsdp2-fa2 — step 117 (X10b training backend: FSDP2 vs Megatron)

GRPO checkpoint from the TaskTrove X10b backend experiment, trained on Iris / CoreWeave (cw-rno2a, 4x8 H100). Base model Qwen/Qwen3-Coder-30B-A3B-Instruct, trained on DCAgent/exp_rpt_multifile with SkyRL + Terminus-2. Single variable vs the X8 longclip base: trainer.strategy=fsdp2 (+ flash-attention-2, async). Campaign verifier is pass_ratio shaping.

Checkpoint selection

global_step_117 was selected by the trailing-5 reward EMA (alpha = 1/3) over the stitched 6-generation curve (steps 1-131, no gaps) — the highest-EMA checkpoint (EMA 0.2535; step reward 0.2793; pass@8 0.3906; entropy 0.0215), inside the reward plateau. Export performed on-Iris from the sharded FSDP checkpoint bank via the checkpoint-export job (hf_upload_mode=latest).

Run status — question ANSWERED; stopped at 131/400 (plateau)

X10b's question — does FSDP2 survive the X8 schedule that collapsed every Megatron arm — is answered yes: 131 stable steps with entropy falling 0.284 -> 0.0129 (~22x, exploration exhausted) and response length held (11.9k -> 13.5k tokens; no length collapse). Reward plateaued from ~step 40 (20-step windows 40-131 flat within noise; peak raw 0.332 at step 116); the remaining horizon buys nothing. Stopped by owner decision 2026-08-15 at logged step 131, banked 129.

See training_logs/ for metrics.csv (stitched per-step curve + trailing-5 EMA), report.md, reward_plot.png, and the launch rl_config.yaml. W&B (dogml/OpenThoughts-Agent): base jjjhduya, final gen r7 0s0kinwg.

Training Traces

penfever/tt-x10-fsdp2-fa2 — 1/8 systematic subsample (every 8th trial of 89,425 across 5 run generations, uniform coverage of steps 1-131). Full-set transfer from CoreWeave object storage was ~430 GB; the subsample is a documented deviation, approved by the owner, for an arm whose question was answered before horizon.

Downloads last month: 141

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for laion/tt-x10-fsdp2-fa2-117-30B

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Finetuned

(85)

this model