Instructions to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine with Transformers:

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

pipe = pipeline("image-text-to-text", model="vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine")
model = AutoModelForMultimodalLM.from_pretrained("vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine

SGLang

How to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine 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 "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine 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 vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine 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 vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine",
    max_seq_length=2048,
)

Docker Model Runner
How to use vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine with Docker Model Runner:
```
docker model run hf.co/vnixxa31/sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine
```

sweep-nep-sft_ministral-3-3b_lora_r32_lr2e4_wd0.01_adamw-torch-fused_cosine / config.json

vnixxa31

(Trained with Unsloth)

b44aaf1 verified 3 months ago

Raw

History Blame Contribute Delete

2.14 kB

	{
	"architectures": [
	"Mistral3ForConditionalGeneration"
	],
	"bos_token_id": 1,
	"torch_dtype": "bfloat16",
	"eos_token_id": 2,
	"image_token_index": 10,
	"model_name": "unsloth/Ministral-3-3B-Base-2512",
	"model_type": "mistral3",
	"multimodal_projector_bias": false,
	"pad_token_id": 11,
	"projector_hidden_act": "gelu",
	"spatial_merge_size": 2,
	"text_config": {
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"torch_dtype": "bfloat16",
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"max_position_embeddings": 262144,
	"model_type": "ministral3",
	"num_attention_heads": 32,
	"num_hidden_layers": 26,
	"num_key_value_heads": 8,
	"pad_token_id": 11,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 16.0,
	"llama_4_scaling_beta": 0.1,
	"mscale": 1.0,
	"mscale_all_dim": 1.0,
	"original_max_position_embeddings": 16384,
	"rope_theta": 1000000.0,
	"rope_type": "yarn",
	"type": "yarn"
	},
	"sliding_window": null,
	"tie_word_embeddings": true,
	"use_cache": true,
	"vocab_size": 131072
	},
	"tie_word_embeddings": true,
	"unsloth_fixed": true,
	"unsloth_version": "2026.3.15",
	"use_cache": false,
	"vision_config": {
	"attention_dropout": 0.0,
	"torch_dtype": "bfloat16",
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 1540,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "pixtral",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"vision_feature_layer": -1
	}