Instructions to use AnandHaridas1980/slm125m-live with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AnandHaridas1980/slm125m-live with Transformers:

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

pipe = pipeline("text-generation", model="AnandHaridas1980/slm125m-live")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AnandHaridas1980/slm125m-live")
model = AutoModelForCausalLM.from_pretrained("AnandHaridas1980/slm125m-live", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AnandHaridas1980/slm125m-live with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AnandHaridas1980/slm125m-live"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AnandHaridas1980/slm125m-live",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AnandHaridas1980/slm125m-live

SGLang

How to use AnandHaridas1980/slm125m-live 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 "AnandHaridas1980/slm125m-live" \
    --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": "AnandHaridas1980/slm125m-live",
		"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 "AnandHaridas1980/slm125m-live" \
        --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": "AnandHaridas1980/slm125m-live",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AnandHaridas1980/slm125m-live with Docker Model Runner:
```
docker model run hf.co/AnandHaridas1980/slm125m-live
```

slm125m-live

A 125M-parameter Llama-architecture language model pretrained from scratch on a legal- and finance-heavy corpus. Trained end to end on Modal; the tokenizer is also trained from scratch on this corpus (16,384-token byte-level BPE).

This is a base model. It has had no instruction tuning, no RLHF, and no safety alignment. At 125M parameters it will confabulate freely — it is a research and teaching artifact, not a source of legal or financial advice.

Architecture


Parameters	125,847,552 (125.8M)
Layers / hidden / heads	12 / 768 / 12 (MHA)
Context length	1024
Vocab	16,384 (byte-level BPE, trained on this corpus)
Position encoding	RoPE (theta 10000)
Activation / norm	SwiGLU / RMSNorm
Tied embeddings	yes

Training data (2.04B unique tokens)

Source	Tokens	Share
case-law	716M	35.1%
sec	860M	42.2%
fineweb-edu	465M	22.8%

Built from HFforLegal/case-law (US court opinions), PleIAs/SEC (SEC filings) and HuggingFaceFW/fineweb-edu (sample-10BT, general fluency filler). The legal sources are the binding constraint: together they hold only ~2B clean tokens, so the mix is "take all the legal text, add a small web slice" rather than a chosen ratio.

Pipeline: stream -> 6-step deterministic clean (line filters, boilerplate strip, 4-gram repetition, ASCII/langdetect English gate, dictionary-based OCR gate on case-law) -> MinHash near-dedup + exact dedup -> 13-gram decontamination against CaseHOLD/LexGLUE -> pack into 1024-token windows, 99/1 train/val split.

Training


Tokens seen	8.16B (4 epochs)
Steps	15,568
Global batch	524,288 tokens
Optimizer	AdamW (betas 0.9/0.95, wd 0.1, clip 1.0)
LR schedule	cosine 0.0006 -> 6e-05, 200M warmup tokens
Precision	bf16 autocast, fp32 master weights
Hardware	8x NVIDIA H100 (DDP, single node)
Final val loss	2.1228

Evaluation (held-out 1% split)

Split	Perplexity
ALL	8.31
case-law	8.68
sec	4.80
fineweb-edu	21.61

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("AnandHaridas1980/slm125m-live")
model = AutoModelForCausalLM.from_pretrained("AnandHaridas1980/slm125m-live")

ids = tok("The plaintiff filed a motion to dismiss on the grounds that", return_tensors="pt")
print(tok.decode(model.generate(**ids, max_new_tokens=60, do_sample=True, top_p=0.95)[0]))

Limitations

Base model, English only, 1024-token context. The case-law source is OCR'd and retains some scanning noise despite the dictionary gate. Training data is skewed to older SEC filings. Do not use for legal or financial advice.

Downloads last month: 566

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for AnandHaridas1980/slm125m-live

Finetunes

1 model

AnandHaridas1980
/

slm125m-live