language, license, library_name, tags, base_model, pipeline_tag, model-index

language	license	library_name	tags	base_model	pipeline_tag	model-index
en	apache-2.0	transformers	toke code-generation programming-language qwen2 qlora fine-tuned awq 4bit	Qwen/Qwen2.5-Coder-7B-Instruct	text-generation	name results toke-7b-gate2 task metrics type name text-generation Code Generation name type value verified Compilation Pass@1 pass@1 100 true name type value verified Functional Pass@1 pass@1 8 true

toke-7b-gate2

A 7B parameter language model fine-tuned to generate code in toke, a programming language designed to reduce token cost of AI-generated code. This model writes syntactically valid toke 100% of the time.

Model Details

Property	Value
Base model	Qwen 2.5 Coder 7B-Instruct
Method	QLoRA (rank 64, alpha 128, 3 epochs)
Training data	25,953 records — 18,890 synthetic + 6,069 from loke production (87K lines)
Training time	37 hours on NVIDIA A10G (24 GB)
Weights	AWQ 4-bit quantized (this repo)
Context length	32,768 tokens
License	Apache 2.0

What is toke?

toke is a statically typed, compiled language with a 55-character alphabet (lowercase a-z, digits 0-9, and 19 symbols). It compiles to native binaries via LLVM. A purpose-built BPE tokenizer achieves 52% fewer tokens on average vs cl100k_base.

• 13 keywords: m f t i if el lp br let mut as rt mt
• No comments in source — documentation lives in companion files (.tkc.md)
• Errors as values — no exceptions, result types with mt (match)
• Website: tokelang.dev | Console: console.tokelang.dev

Gate 2 Results (May 2026)

Metric	Gate 1	Gate 2
Compilation Pass@1	63.7%	100%
Tasks evaluated	1,000	700
Functional Pass@1	—	~8%
Training records	73,000	25,953

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("karwalski/toke", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("karwalski/toke")

prompt = """<|im_start|>system
Write toke programs. m=mod; f=name(p:type):ret{body}; let x=42; <expr return. Semicolons everywhere. Start with m=.
<|im_end|>
<|im_start|>user
Write a hello world program
<|im_end|>
<|im_start|>assistant
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.2, do_sample=True)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# m=hello;i=io:std.io;f=main():i64{io.println("hello world");<0};

API Access

Free API access via console.tokelang.dev — no credit card required.

curl -X POST https://api.tokelang.dev/v1/generate \
  -H "X-Api-Key: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"description": "Return the absolute value of an integer"}'

Links

• tokelang.dev — Project website
• console.tokelang.dev — Free API access
• GitHub: toke — Compiler, spec, stdlib
• GitHub: loke — 87K lines of production toke
• Live tokenizer — Compare token counts in-browser