Instructions to use alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron with Transformers:

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

pipe = pipeline("text-generation", model="alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron")
model = AutoModelForCausalLM.from_pretrained("alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron", 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 alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron

SGLang

How to use alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron 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 "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron" \
    --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": "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron",
		"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 "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron" \
        --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": "alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron with Docker Model Runner:
```
docker model run hf.co/alexjerpelea/Qwen3.5-4B-en-es-fa-hi-ron
```

alexjerpelea commited on Apr 23

Commit

a875b64

verified ·

1 Parent(s): 9738a86

add model card with results matrix + training details

Browse files

Files changed (1) hide show

README.md +53 -0

README.md ADDED Viewed

	@@ -0,0 +1,53 @@

+---
+license: apache-2.0
+library_name: transformers
+base_model: Qwen/Qwen3.5-4B
+language:
+- en
+- es
+- fa
+- hi
+- ro
+tags:
+- continual-learning
+- sft
+- affective-state-identification
+- multilingual
+---
+# Qwen3.5-4B day-by-day multilingual SFT (en -> es -> fa -> hi -> ro)
+Qwen3.5-4B fine-tuned sequentially on 5 languages for a continual-learning
+"day in the life" experiment. Each language trained for one "day"
+(3 epochs, 1000 train rows), starting from the previous day's checkpoint.
+This checkpoint is the end of day 5 (Romanian) - the model has seen all
+5 languages in order.
+**Task:** Fill [MASK] tokens in an "I feel ..." sentence with the
+corresponding affective state expression(s).
+## Results - set_acc@1 on held-out test sets (1000 rows/lang)
+```
+                test_en   test_es   test_fa   test_hi   test_ro
+day1 (en)       0.187*    0.149     0.114     0.117     0.121
+day2 (->es)     0.192     0.267*    0.112     0.088     0.090
+day3 (->fa)     0.166     0.231     0.445*    0.068     0.111
+day4 (->hi)     0.157     0.234     0.315     0.571*    0.174
+day5 (->ro)     0.144     0.167     0.358     0.533     0.443*
+```
+`*` = just-trained language. This checkpoint corresponds to the final row.
+## Training details
+- Base: `Qwen/Qwen3.5-4B`
+- Order: en -> es -> fa -> hi -> ro (one language per day)
+- Per day: 3 epochs, effective bs 4 (per_device=1, grad_accum=4)
+- LR 1e-5, cosine, warmup 0.03, bf16, sdpa attention, gradient checkpointing
+- Single A100-40GB SXM
+## Code and full run log
+https://github.com/Continual-Learning-Emotion-Group/Romanian_ASI/tree/day-by-day
+See `pipeline/train/RUN_LOG_DAY_BY_DAY.md`.