Instructions to use freakyskittle/oxidize-trader-7m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use freakyskittle/oxidize-trader-7m with Transformers:

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

pipe = pipeline("text-generation", model="freakyskittle/oxidize-trader-7m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("freakyskittle/oxidize-trader-7m")
model = AutoModelForCausalLM.from_pretrained("freakyskittle/oxidize-trader-7m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use freakyskittle/oxidize-trader-7m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "freakyskittle/oxidize-trader-7m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "freakyskittle/oxidize-trader-7m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/freakyskittle/oxidize-trader-7m

SGLang

How to use freakyskittle/oxidize-trader-7m 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 "freakyskittle/oxidize-trader-7m" \
    --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": "freakyskittle/oxidize-trader-7m",
		"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 "freakyskittle/oxidize-trader-7m" \
        --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": "freakyskittle/oxidize-trader-7m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use freakyskittle/oxidize-trader-7m with Docker Model Runner:
```
docker model run hf.co/freakyskittle/oxidize-trader-7m
```

oxidize-trader-7m

From-scratch GPT trained with oxidize-training (C + OpenBLAS). 7,432,704 parameters, F32.

This model was mainly for research and is NOT supposed to be used at all for anything. Can only be used in Oxidize-c (github.com/Zapdev-labs/Oxidize.git)

Weights are in model.safetensors as GPT-2 tensors (Conv1D layout, tied wte). Native trader.bin (OXTR) and vocab.bin are included for the C trainer.

It is a language model of ticket text, not a working stock picker.

Files

File	What
`model.safetensors`	GPT-2 F32 weights (29 MB)
`config.json`	`GPT2LMHeadModel`, 8L / 8H / 256d / 4096 vocab
`tokenizer.json` / `vocab.json` / `merges.txt`	byte-level BPE (ids match C `vocab.bin`)
`generation_config.json`	greedy, BOS 256, EOS 257
`trader.bin`	original OXTR checkpoint
`vocab.bin`	original C BPE merges

Load

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "freakyskittle/oxidize-trader-7m"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)
ids = tok("AAPL 2026-09-10 close 228 RSI 32 NEWS: fed holds. ACTION=", return_tensors="pt")
out = model.generate(**ids, max_new_tokens=16)
print(tok.decode(out[0], skip_special_tokens=True))

Or the C trainer:

./oxidize-training/bin/oxidize-training sample \
  --ckpt trader.bin --vocab vocab.bin \
  --prompt "AAPL 2026-09-10 close 228 RSI 32 NEWS: fed holds. ACTION="

Size

8 layers, 8 heads, width 256, context 256, vocab 4096. GELU-tanh (gelu_new). Tied embeddings. Train: 2200 steps, loss 8.32 → 3.89.

What it actually is

Tickets look like SYM … NEWS: … ACTION=BUY|SELL|HOLD. Labels are next-day close vs ±0.6%. Last picks run printed BUY on all 20 names. Do not size real money.

Downloads last month: 240

Safetensors

Model size

7.43M params

Tensor type

F32