Instructions to use z-coder/Magma-8B-modified with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use z-coder/Magma-8B-modified with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="z-coder/Magma-8B-modified", trust_remote_code=True) 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 AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("z-coder/Magma-8B-modified", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use z-coder/Magma-8B-modified with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "z-coder/Magma-8B-modified" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "z-coder/Magma-8B-modified", "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/z-coder/Magma-8B-modified
- SGLang
How to use z-coder/Magma-8B-modified 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 "z-coder/Magma-8B-modified" \ --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": "z-coder/Magma-8B-modified", "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 "z-coder/Magma-8B-modified" \ --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": "z-coder/Magma-8B-modified", "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" } } ] } ] }' - Docker Model Runner
How to use z-coder/Magma-8B-modified with Docker Model Runner:
docker model run hf.co/z-coder/Magma-8B-modified
| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "microsoft/Magma-8B--configuration_magma.MagmaConfig", | |
| "AutoModelForCausalLM": "microsoft/Magma-8B--modeling_magma.MagmaForCausalLM" | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "image_token_id": 128257, | |
| "img_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mm_use_image_history": true, | |
| "mm_use_image_start_end": true, | |
| "mm_use_trace_speed": true, | |
| "mm_use_trace_start_end": false, | |
| "model_type": "causal_lm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "remove_static_trace_pts": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "spatial_quant_size": 256, | |
| "text_config": { | |
| "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128009, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 128256, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "vocab_size": 128261 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.0.dev0", | |
| "use_cache": false, | |
| "vision_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128009, | |
| "feature_outs": "encoder", | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "image_aspect_ratio": "square", | |
| "img_anyres_strategy": "crop", | |
| "img_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_num_crops": 4, | |
| "max_position_embeddings": 8192, | |
| "mm_hidden_size": 3072, | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_use_row_seperator": true, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "model_type": "causal_lm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "proj_vis_to_txt_tokens": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 4096, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vision_tokenizer": "all", | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vision_backbone": "convnextxxlarge", | |
| "vision_feature_layer": "clip_vis_dense", | |
| "vision_tokenizer_lr": null, | |
| "vocab_size": 128257 | |
| }, | |
| "vocab_size": 128320 | |
| } |