Instructions to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "alvaro-mazcu/Qwen3-4B-Instruct-FineTome")

Transformers

How to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome with Transformers:

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

pipe = pipeline("text-generation", model="alvaro-mazcu/Qwen3-4B-Instruct-FineTome")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alvaro-mazcu/Qwen3-4B-Instruct-FineTome", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alvaro-mazcu/Qwen3-4B-Instruct-FineTome

SGLang

How to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome 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 "alvaro-mazcu/Qwen3-4B-Instruct-FineTome" \
    --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": "alvaro-mazcu/Qwen3-4B-Instruct-FineTome",
		"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 "alvaro-mazcu/Qwen3-4B-Instruct-FineTome" \
        --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": "alvaro-mazcu/Qwen3-4B-Instruct-FineTome",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alvaro-mazcu/Qwen3-4B-Instruct-FineTome with Docker Model Runner:
```
docker model run hf.co/alvaro-mazcu/Qwen3-4B-Instruct-FineTome
```

alvaro-mazcu commited on Nov 29, 2025

Commit

40eae9c

verified ·

1 Parent(s): 056d767

Upload fine-tuned weights

Browse files

Files changed (10) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
optimizer.pt +1 -1
rng_state_0.pth +3 -0
rng_state_1.pth +3 -0
rng_state_2.pth +3 -0
rng_state_3.pth +3 -0
scheduler.pt +1 -1
trainer_state.json +0 -0
training_args.bin +1 -1

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "up_proj",
     "gate_proj",
     "v_proj",
     "k_proj",
-    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a7d01ab928c70419e25980bc436c1d1dde1839f70f9814e4b21be5e76a6d8d
 size 132187888

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de79e405e02fc7c5c5eddfb81a7dd7b434a9711deb27096412cc809bac9bf7a
 size 264665722

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

+version https://git-lfs.github.com/spec/v1
+oid sha256:5601f15f52ba0d8ad0112af3483c8dc68b69980761aaa00ba8e2e0934620ab2e
+size 15024

 version https://git-lfs.github.com/spec/v1
+oid sha256:f11a52a18071568303536ae9be838a3ecfa3317a8aece3d9e9314a2d12d64b9a
 size 5752

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@