Instructions to use amirhosseinjpl/jplstar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amirhosseinjpl/jplstar with Transformers:

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

pipe = pipeline("text-generation", model="amirhosseinjpl/jplstar")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amirhosseinjpl/jplstar")
model = AutoModelForCausalLM.from_pretrained("amirhosseinjpl/jplstar", 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 amirhosseinjpl/jplstar with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/amirhosseinjpl/jplstar

SGLang

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

Docker Model Runner
How to use amirhosseinjpl/jplstar with Docker Model Runner:
```
docker model run hf.co/amirhosseinjpl/jplstar
```

Telisk 1.0 — JPLSTAR

Fine-tune of Qwen/Qwen2.5-7B-Instruct for Standard Persian → Abizi.
Qaeni is treated as a closely related South Khorasan variety in the training mix, not as a separately scored test language.

Trained with Unsloth QLoRA on 2× NVIDIA T4 (Kaggle). Adapter merged. Repo: amirhosseinjpl/jplstar.

This is a dialect transfer model. It is not a general chatbot. Without the system turn used at train time, the base Qwen identity can reappear. That is expected.

Inference (matches eval)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "amirhosseinjpl/jplstar"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype=torch.bfloat16, device_map="auto"
)

messages = [
    {
        "role": "system",
        "content": "Translate the following Standard Persian sentence into Abizi dialect.",
    },
    {"role": "user", "content": "دیشب رفتم مغازه."},
]

prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(
    **inputs,
    max_new_tokens=128,
    do_sample=False,
    pad_token_id=tok.eos_token_id,
)
print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Greedy decoding is what produced the numbers below. Sampling is for the demo Space only.

Splits

Held-out rows were isolated from train-Final. No reverse-pair cut from the same sentence into eval.

split	n	file
train	10,207	train-Final.jsonl
valid	30	valid-Final.jsonl
test	50	test_data_for_v4

Eval

Metric: character overlap (F1 over character bags after yeh/kaf normalize). Exact match is the wrong headline: Abizi spelling is not stable.

split	exact	overlap
valid	0/30	81.5%
test	0/50	85.8%

Valid is a 30-row file. Do not cite a 50-row file as valid. Test > valid on this metric is compatible with split difficulty and small-n noise. It is not proof of generalization. Human gold-vs-pred is the judge. Overlap is a proxy. Not BLEU.