Instructions to use timothywong731/tim-360m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timothywong731/tim-360m-base with Transformers:

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

pipe = pipeline("text-generation", model="timothywong731/tim-360m-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("timothywong731/tim-360m-base")
model = AutoModelForCausalLM.from_pretrained("timothywong731/tim-360m-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timothywong731/tim-360m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timothywong731/tim-360m-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timothywong731/tim-360m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timothywong731/tim-360m-base

SGLang

How to use timothywong731/tim-360m-base 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 "timothywong731/tim-360m-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timothywong731/tim-360m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "timothywong731/tim-360m-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timothywong731/tim-360m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use timothywong731/tim-360m-base with Docker Model Runner:
```
docker model run hf.co/timothywong731/tim-360m-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TIM-360M-base

A 361.8M-parameter decoder-only transformer, trained from scratch on ~30B tokens on 2× RTX 4090. Part of TIM (Transformer Inference Model) — an end-to-end, from-scratch LLM built to be legible and honestly evaluated.

Exported as Qwen3ForCausalLM — it loads with transformers and no trust_remote_code.

Architecture

SmolLM2-360M skeleton with modern choices: pre-LN RMSNorm, RoPE (θ=100000), SwiGLU, grouped-query attention (15 query / 5 KV heads) with per-head QK-norm, tied embeddings, no biases. 32 layers, hidden 960, head_dim 64, FFN 2560, vocab 49,152 (byte-level BPE). Context: max_position_embeddings 4096, trained at seq_len 2048.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("timothywong731/tim-360m-base")
m = AutoModelForCausalLM.from_pretrained("timothywong731/tim-360m-base", torch_dtype=torch.bfloat16)
ids = tok("The capital of France is", return_tensors="pt")
print(tok.decode(m.generate(**ids, max_new_tokens=20)[0]))

Training

~30B tokens, mix: 70% web (FineWeb-Edu sample-100BT + DCLM-Baseline), 15% Stack-Edu (code), 10% FineMath-3+, 5% misc. Muon + AdamW, WSD (warmup–stable–decay) schedule, bf16, 2× RTX 4090 (DDP, no NVLink).

Evaluation

lm-evaluation-harness (0.4.12), 0-shot, acc_norm where applicable:

HellaSwag	ARC-Easy	ARC-Challenge	PIQA	WinoGrande	OpenBookQA	SciQ	SocialIQA	CommonsenseQA	WikiText (bpb ↓)
0.388	0.515	0.259	0.658	0.525	0.294	0.722	0.378	0.196	1.058

Healthy for the scale: at 30B tokens this is **130× less training data** than SmolLM2-360M (4T). Near-parity on early-saturating tasks (PIQA, SciQ), a real gap on token-hungry ones (HellaSwag, ARC) — as the token budget predicts.

Limitations

Small (360M) and lightly trained (~30B tokens). Not instruction-tuned — this is the base model. Weak at arithmetic and multi-step reasoning; will hallucinate facts; English-only; no safety tuning — do not deploy to end users without your own filtering.

Provenance & license

Apache-2.0. Trained only on named, public datasets: FineWeb-Edu (ODC-BY), DCLM-Baseline (CC-BY-4.0), Stack-Edu (derived from The Stack v2), FineMath (ODC-BY). No gated or scraped-private data. Attribution and removal requests: open an issue on the source repository.

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for timothywong731/tim-360m-base

Finetunes

1 model

Quantizations

1 model

Datasets used to train timothywong731/tim-360m-base

Evaluation results

acc_norm on HellaSwag (0-shot)
self-reported

0.388
acc_norm on ARC-Easy (0-shot)
self-reported

0.515
acc_norm on ARC-Challenge (0-shot)
self-reported

0.259
acc_norm on PIQA (0-shot)
self-reported

0.658
acc on WinoGrande (0-shot)
self-reported

0.525
acc_norm on OpenBookQA (0-shot)
self-reported

0.294
acc_norm on SciQ (0-shot)
self-reported

0.722