Instructions to use tohio/slm-gpt-127m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tohio/slm-gpt-127m-base with Transformers:

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

pipe = pipeline("text-generation", model="tohio/slm-gpt-127m-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tohio/slm-gpt-127m-base")
model = AutoModelForCausalLM.from_pretrained("tohio/slm-gpt-127m-base", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tohio/slm-gpt-127m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tohio/slm-gpt-127m-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tohio/slm-gpt-127m-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tohio/slm-gpt-127m-base

SGLang

How to use tohio/slm-gpt-127m-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 "tohio/slm-gpt-127m-base" \
    --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": "tohio/slm-gpt-127m-base",
		"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 "tohio/slm-gpt-127m-base" \
        --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": "tohio/slm-gpt-127m-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tohio/slm-gpt-127m-base with Docker Model Runner:
```
docker model run hf.co/tohio/slm-gpt-127m-base
```

tohio/slm-gpt-127m-base

tohio/slm-gpt-127m-base is a pre-trained base language model (127M, ~126.8M parameters) trained from scratch on a 10B token educational and reasoning curriculum. This checkpoint serves as the foundational base and has not undergone instruction tuning or alignment.

Architecture Highlights

Parameters: ~126.8M (14 layers, hidden dimension d_model = 768)
Attention: Grouped-Query Attention (GQA, 12:4 ratio)
Activation: SwiGLU Feed-Forward Network (d_ffn = 2048)
Positional Encoding: Rotary Position Embeddings (RoPE)
Normalization: Bias-free Pre-LayerNorm / RMSNorm
Weight Tying: Tied input embedding (embed_tokens) and output head (lm_head)
Hugging Face Native: Directly compatible with LlamaForCausalLM

Pre-training Curriculum

The base representation was pre-trained across an interleaved multi-source domain mixture (10B tokens):

FineWeb-Edu
DCLM-Edu
The Stack-Edu
NuminaMath-CoT
OpenMathReasoning
SLM-Synthetic-Pretrain

Pipeline Lineage

Pre-training (tohio/slm-gpt-127m-base): Completed 10B tokens over packed memory-mapped token shards.
Supervised Fine-Tuning (SFT): See tohio/slm-gpt-127m-sft.
Direct Preference Optimization (DPO): See tohio/slm-gpt-127m-dpo.

Prompt Format (Raw Completion)

As an unaligned base model, this checkpoint performs raw document continuation rather than dialogue:

The key difference between a compiler and an interpreter is that

Quick Start via `transformers`

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tohio/slm-gpt-127m-base"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

prompt = "The key difference between a compiler and an interpreter is that"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=64, temperature=0.7, top_p=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Trained and published autonomously via slm-gpt.

Downloads last month: 257

Safetensors

Model size

0.1B params

Tensor type

BF16

tohio
/

slm-gpt-127m-base

tohio/slm-gpt-127m-base

Architecture Highlights

Pre-training Curriculum

Pipeline Lineage

Prompt Format (Raw Completion)

Quick Start via `transformers`

Datasets used to train tohio/slm-gpt-127m-base

tohio/slm-gpt-127m-base

Architecture Highlights

Pre-training Curriculum

Pipeline Lineage

Prompt Format (Raw Completion)

Quick Start via transformers

Datasets used to train tohio/slm-gpt-127m-base

Quick Start via `transformers`