Instructions to use teaguesterling/qwen3.5-4b-astcss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teaguesterling/qwen3.5-4b-astcss with Transformers:

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

pipe = pipeline("text-generation", model="teaguesterling/qwen3.5-4b-astcss")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teaguesterling/qwen3.5-4b-astcss")
model = AutoModelForCausalLM.from_pretrained("teaguesterling/qwen3.5-4b-astcss", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teaguesterling/qwen3.5-4b-astcss with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teaguesterling/qwen3.5-4b-astcss"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teaguesterling/qwen3.5-4b-astcss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/teaguesterling/qwen3.5-4b-astcss

SGLang

How to use teaguesterling/qwen3.5-4b-astcss 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 "teaguesterling/qwen3.5-4b-astcss" \
    --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": "teaguesterling/qwen3.5-4b-astcss",
		"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 "teaguesterling/qwen3.5-4b-astcss" \
        --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": "teaguesterling/qwen3.5-4b-astcss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use teaguesterling/qwen3.5-4b-astcss with Docker Model Runner:
```
docker model run hf.co/teaguesterling/qwen3.5-4b-astcss
```

qwen3.5-4b-astcss

English → astcss selector (sitting_duck's ast_select) at 4B. The strongest model we have on the base selector eval.

Scores

Measured on this merged artifact, scored in NF4 to match how the adapter was measured. A merge is verified, not assumed — and this one is not identity:

eval	this model	the adapter it came from
108-pair selector eval	88.9 % (96/108)	89.8 % (97/108)
`eval_t5` — 55 harder, relational selectors	65.5 % (36/55)	67.3 % (37/55)

The merge cost exactly one pair on each eval. That is within noise, but it is real: this adapter was fitted against NF4 weights, and folding it into fp16 is a lossy operation. verify_merge shows why the check matters — 248 targeted tensors at max |Δ| 0.0031 against 178 untouched at 0.00049. The targeted deltas are only ~6× the fp16 round-trip floor, a far narrower margin than an fp16-trained adapter gives.

Tier breakdown on the 108-pair eval: 21/21, 20/25, 28/31, 27/31.

Scoring is by execution — the selector runs against the fixture and the returned node set is compared to the reference, so a different string selecting the same nodes counts as correct.

Read this before assuming bigger is better

On the harder eval_t5, a 0.8B model (qwen3.5-0.8b-astcss-t5) scores 83.6 % against this model's 65.5 %. That 0.8B is five times smaller and wins by 18 points, because it was trained on a 7.4× larger corpus. This 4B was trained on the older, smaller one.

Corpus beat parameter count, decisively, on the eval that discriminates. Use this model for the basic selector eval; use the 0.8B for relational and compound selectors.

It needs the card

0.0 % without its system prompt, at every model size tested. Trained with a per-language vocabulary card in the system position. Cards live in the astcss-eval repo under train/cards/card_<lang>.md.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

m = "teaguesterling/qwen3.5-4b-astcss"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, dtype=torch.float16, device_map="cuda")

card = open("train/cards/card_python.md").read()   # REQUIRED
msgs = [{"role": "system", "content": card},
        {"role": "user", "content": "functions that call range without any try block"}]
ids = tok(tok.apply_chat_template(msgs, add_generation_prompt=True, tokenize=False),
          return_tensors="pt").to(model.device)
out = model.generate(**ids, max_new_tokens=48, do_sample=False)
print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))
# .fn:has(.call#range):not(:has(.try))

Greedy decoding, thinking off, ~5 completion tokens per answer.

What it is

QLoRA (r=16, α=32, all-linear) on Qwen3.5-4B in NF4, 2 epochs, per-language card, template cap 8. Merged into the base weights — no adapter at serving time.

Limitations

Text-only. 312 base tensors are not written: the vision tower (model.visual.*) and the multi-token-prediction head (mtp.*) are dropped by save_pretrained under AutoModelForCausalLM.
Needs the card. Not a general chat model.
NF4-fitted, fp16-merged. Scored here in NF4; fp16 inference may differ slightly.
Beaten on relational selectors by a model five times smaller — see above.

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

F16

Model tree for teaguesterling/qwen3.5-4b-astcss

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(671)

this model