Instructions to use Ba2han/mistral_augment-multi-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/mistral_augment-multi-ft with Transformers:

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

pipe = pipeline("image-text-to-text", model="Ba2han/mistral_augment-multi-ft")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Ba2han/mistral_augment-multi-ft")
model = AutoModelForImageTextToText.from_pretrained("Ba2han/mistral_augment-multi-ft")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ba2han/mistral_augment-multi-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/mistral_augment-multi-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/mistral_augment-multi-ft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/mistral_augment-multi-ft

SGLang

How to use Ba2han/mistral_augment-multi-ft 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 "Ba2han/mistral_augment-multi-ft" \
    --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": "Ba2han/mistral_augment-multi-ft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Ba2han/mistral_augment-multi-ft" \
        --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": "Ba2han/mistral_augment-multi-ft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio new

How to use Ba2han/mistral_augment-multi-ft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/mistral_augment-multi-ft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/mistral_augment-multi-ft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/mistral_augment-multi-ft to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/mistral_augment-multi-ft",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/mistral_augment-multi-ft with Docker Model Runner:
```
docker model run hf.co/Ba2han/mistral_augment-multi-ft
```

Ba2han commited on Dec 22, 2025

Commit

bbddfed

verified ·

1 Parent(s): be57e31

Training in progress, step 5123

Browse files

Files changed (5) hide show

README.md +17 -82
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

README.md CHANGED Viewed

@@ -15,96 +15,31 @@ licence: license
 This model is a fine-tuned version of [unsloth/Ministral-3-8B-Base-2512](https://huggingface.co/unsloth/Ministral-3-8B-Base-2512).
 It has been trained using [TRL](https://github.com/huggingface/trl).
-```
-'Görev: Metni etiketle, özetle, trivia hazırla ve terimleri çevir.'
-'Görev: Metni etiketle ve İngilizceye çevir.'
----
-'Görev: Metinden soru ve cevaplar hazırla.
-Hedef uzunluk: kısa'
-'Görev: Metinden soru ve cevaplar hazırla.
-Hedef uzunluk: orta'
-'Görev: Metinden soru ve cevaplar hazırla.
-Hedef uzunluk: uzun'
----
-'Görev: Metni etiketle ve özetle.
-Hedef uzunluk: kısa'
-'Görev: Metni etiketle ve özetle.
-Hedef uzunluk: orta'
-'Görev: Metni etiketle ve özetle.
-Hedef uzunluk: uzun'
----
-'Görev: Metni etiketle ve bir makale oluştur.
-Hedef uzunluk: kısa'
-'Görev: Metni etiketle ve bir makale oluştur.
-Hedef uzunluk: orta'
-'Görev: Metni etiketle ve bir makale oluştur.
-Hedef uzunluk: uzun'
----
-'Görev: Metinden bir iç konuşma (monolog) hazırla.
-Hedef uzunluk: kısa'
-'Görev: Metinden bir iç konuşma (monolog) hazırla.
-Hedef uzunluk: orta'
-'Görev: Metinden bir iç konuşma (monolog) hazırla.
-Hedef uzunluk: uzun'
----
-'Görev: Metinden bir diyalog hazırla.
-Hedef uzunluk: kısa'
-'Görev: Metinden bir diyalog hazırla.
-Hedef uzunluk: orta'
-'Görev: Metinden bir diyalog hazırla.
-Hedef uzunluk: uzun'
----
-'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
-Hedef uzunluk: kısa'
-'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
-Hedef uzunluk: orta'
-'Görev: Metinden Kullanıcı/Asistan diyaloğu üret.
-Hedef uzunluk: uzun'
----
-'Görev: Duygu analizi yap ve paragraf hâlinde çevir.
-Hedef uzunluk: yok'
-'Görev: Metni etiketle ve çevir.
-Hedef uzunluk: yok'
----
-'Görev: Metni etiketle ve soru cevaplar hazırla.
-Hedef uzunluk: kısa'
-'Görev: Metni etiketle ve soru cevaplar hazırla.
-Hedef uzunluk: orta'
-'Görev: Metni etiketle ve soru cevaplar hazırla.
-Hedef uzunluk: uzun'
-```
 ## Citations

 This model is a fine-tuned version of [unsloth/Ministral-3-8B-Base-2512](https://huggingface.co/unsloth/Ministral-3-8B-Base-2512).
 It has been trained using [TRL](https://github.com/huggingface/trl).
+## Quick start
+```python
+from transformers import pipeline
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Ba2han/mistral_augment-multi-ft", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/7gnkzia9)
+This model was trained with SFT.
+### Framework versions
+- TRL: 0.24.0
+- Transformers: 5.0.0.dev0
+- Pytorch: 2.9.1
+- Datasets: 4.3.0
+- Tokenizers: 0.22.1
 ## Citations

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a6e1a1b298ef80cc34f46b84b45192ac8f5a2b8d23fc648b432b5d5102e8a9
 size 4999724576

 version https://git-lfs.github.com/spec/v1
+oid sha256:c5884a2b2d0cb5f9f7ca81335e3b0d762d15b2252db21b4779820322b56e2f89
 size 4999724576

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99c81efa1cf2db91edd08804a6edf90629fc35ac9017b14872d31fc6d351902
 size 4999820896

 version https://git-lfs.github.com/spec/v1
+oid sha256:79ff0c366937267e75c580f2bea22c720ba07e29d85ee8f3ee4d640d862f0ded
 size 4999820896

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219a57419ea6b465fe73c6c8a29724509cf28fda8785f577a369994d5dd94249
 size 4915917688

 version https://git-lfs.github.com/spec/v1
+oid sha256:42787d9c96a32b393520a969b248710e8e163537f516a09795a30a71fee21a8f
 size 4915917688

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0499b38214488972101a719d1ee39d809599162ebea003af500a0a496be529e8
 size 2920659992

 version https://git-lfs.github.com/spec/v1
+oid sha256:ce62f63d3d702fc3e51d44d342fcda4fc690231d3b3e7f9eb9c2c5b6f38f0fb1
 size 2920659992