Image-Text-to-Text
Transformers
Safetensors
qwen3_5
text-generation-inference
unsloth
qwen3.5
conversational
Instructions to use armand0e/Qwen3.5-27B-MiniMax-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use armand0e/Qwen3.5-27B-MiniMax-Coder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="armand0e/Qwen3.5-27B-MiniMax-Coder") 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("armand0e/Qwen3.5-27B-MiniMax-Coder") model = AutoModelForImageTextToText.from_pretrained("armand0e/Qwen3.5-27B-MiniMax-Coder") 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 armand0e/Qwen3.5-27B-MiniMax-Coder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "armand0e/Qwen3.5-27B-MiniMax-Coder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "armand0e/Qwen3.5-27B-MiniMax-Coder", "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/armand0e/Qwen3.5-27B-MiniMax-Coder
- SGLang
How to use armand0e/Qwen3.5-27B-MiniMax-Coder 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 "armand0e/Qwen3.5-27B-MiniMax-Coder" \ --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": "armand0e/Qwen3.5-27B-MiniMax-Coder", "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 "armand0e/Qwen3.5-27B-MiniMax-Coder" \ --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": "armand0e/Qwen3.5-27B-MiniMax-Coder", "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
How to use armand0e/Qwen3.5-27B-MiniMax-Coder 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 armand0e/Qwen3.5-27B-MiniMax-Coder 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 armand0e/Qwen3.5-27B-MiniMax-Coder to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for armand0e/Qwen3.5-27B-MiniMax-Coder to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="armand0e/Qwen3.5-27B-MiniMax-Coder", max_seq_length=2048, ) - Docker Model Runner
How to use armand0e/Qwen3.5-27B-MiniMax-Coder with Docker Model Runner:
docker model run hf.co/armand0e/Qwen3.5-27B-MiniMax-Coder
Upload merged Qwen3.5-27B + MiniMax-Coder (16-bit)
Browse files- config.json +4 -4
- generation_config.json +1 -1
- tokenizer_config.json +2 -3
config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3_5ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"
|
| 6 |
"image_token_id": 248056,
|
| 7 |
"model_type": "qwen3_5",
|
| 8 |
"pad_token_id": 248055,
|
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"attention_dropout": 0.0,
|
| 12 |
"attn_output_gate": true,
|
| 13 |
"bos_token_id": null,
|
| 14 |
-
"
|
| 15 |
"eos_token_id": 248044,
|
| 16 |
"full_attention_interval": 4,
|
| 17 |
"head_dim": 256,
|
|
@@ -118,13 +118,13 @@
|
|
| 118 |
"vocab_size": 248320
|
| 119 |
},
|
| 120 |
"tie_word_embeddings": false,
|
| 121 |
-
"transformers_version": "5.
|
| 122 |
"unsloth_fixed": true,
|
| 123 |
"video_token_id": 248057,
|
| 124 |
"vision_config": {
|
| 125 |
"deepstack_visual_indexes": [],
|
| 126 |
"depth": 27,
|
| 127 |
-
"
|
| 128 |
"hidden_act": "gelu_pytorch_tanh",
|
| 129 |
"hidden_size": 1152,
|
| 130 |
"in_channels": 3,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3_5ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
+
"dtype": "float16",
|
| 6 |
"image_token_id": 248056,
|
| 7 |
"model_type": "qwen3_5",
|
| 8 |
"pad_token_id": 248055,
|
|
|
|
| 11 |
"attention_dropout": 0.0,
|
| 12 |
"attn_output_gate": true,
|
| 13 |
"bos_token_id": null,
|
| 14 |
+
"dtype": "float16",
|
| 15 |
"eos_token_id": 248044,
|
| 16 |
"full_attention_interval": 4,
|
| 17 |
"head_dim": 256,
|
|
|
|
| 118 |
"vocab_size": 248320
|
| 119 |
},
|
| 120 |
"tie_word_embeddings": false,
|
| 121 |
+
"transformers_version": "5.2.0",
|
| 122 |
"unsloth_fixed": true,
|
| 123 |
"video_token_id": 248057,
|
| 124 |
"vision_config": {
|
| 125 |
"deepstack_visual_indexes": [],
|
| 126 |
"depth": 27,
|
| 127 |
+
"dtype": "float16",
|
| 128 |
"hidden_act": "gelu_pytorch_tanh",
|
| 129 |
"hidden_size": 1152,
|
| 130 |
"in_channels": 3,
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "5.
|
| 13 |
}
|
|
|
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.2.0"
|
| 13 |
}
|
tokenizer_config.json
CHANGED
|
@@ -29,6 +29,5 @@
|
|
| 29 |
"unk_token": null,
|
| 30 |
"video_token": "<|video_pad|>",
|
| 31 |
"vision_bos_token": "<|vision_start|>",
|
| 32 |
-
"vision_eos_token": "<|vision_end|>"
|
| 33 |
-
|
| 34 |
-
}
|
|
|
|
| 29 |
"unk_token": null,
|
| 30 |
"video_token": "<|video_pad|>",
|
| 31 |
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
|
|