Instructions to use etanlightstone/simple-lm-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use etanlightstone/simple-lm-v2 with Transformers:

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

pipe = pipeline("text-generation", model="etanlightstone/simple-lm-v2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("etanlightstone/simple-lm-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use etanlightstone/simple-lm-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "etanlightstone/simple-lm-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "etanlightstone/simple-lm-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/etanlightstone/simple-lm-v2

SGLang

How to use etanlightstone/simple-lm-v2 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 "etanlightstone/simple-lm-v2" \
    --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": "etanlightstone/simple-lm-v2",
		"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 "etanlightstone/simple-lm-v2" \
        --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": "etanlightstone/simple-lm-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use etanlightstone/simple-lm-v2 with Docker Model Runner:
```
docker model run hf.co/etanlightstone/simple-lm-v2
```

SimpleLM

Custom decoder-only Transformer language model (pretraining checkpoint). Architecture is defined in modeling_simple_lm.py (bundled in this repo) and loaded via trust_remote_code=True.

Source checkpoint: checkpoints/lm_checkpoint_008_shutdown.pt

This model is a pre-trained only LLM that was trained from scratch on a very small dataset of conversations (found on Kaggle and mixed with OpenAssistant/oasst2). As well as as subset of Finweb_Edu data. This particular save is checkpoint after 1 full epoch. Alltogether about 410M tokens (1B+ would have been more ideal for a model this size).

Architecture

field	value
vocab_size	32000
context_length	512
d_model	768
n_layers	12
n_heads	8
d_ff	2048
activation	gelu
bias	True
tie_word_embeddings	True

Tokenizer source: TinyLlama/TinyLlama-1.1B-Chat-v1.0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "etanlightstone/simple-lm-v2"
tok   = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True)

prompt = "Once upon a time"
ids = tok(prompt, return_tensors="pt").input_ids
out = model.generate(ids, max_new_tokens=80, do_sample=True, top_k=50, temperature=0.9)
print(tok.decode(out[0], skip_special_tokens=True))

Training settings

{
  "batch_size": 10,
  "batch_size_note": "per GPU when using torchrun",
  "world_size": 1,
  "learning_rate": 0.0003,
  "weight_decay": 0.01,
  "num_epochs": 3,
  "max_steps": null,
  "grad_clip": 1.0,
  "seed": 42,
  "docs_dir": "/home/etan/simple_llm/docs",
  "block_size": 512,
  "stride": 448,
  "stride_overlap_tokens": 64
}

Downloads last month: 43

Safetensors

Model size

91.1M params

Tensor type

F32