Instructions to use Brucamian/70-qwen15-55-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Brucamian/70-qwen15-55-R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Brucamian/70-qwen15-55-R") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Brucamian/70-qwen15-55-R", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Brucamian/70-qwen15-55-R with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Brucamian/70-qwen15-55-R" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Brucamian/70-qwen15-55-R", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Brucamian/70-qwen15-55-R
- SGLang
How to use Brucamian/70-qwen15-55-R 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 "Brucamian/70-qwen15-55-R" \ --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": "Brucamian/70-qwen15-55-R", "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 "Brucamian/70-qwen15-55-R" \ --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": "Brucamian/70-qwen15-55-R", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Brucamian/70-qwen15-55-R with Docker Model Runner:
docker model run hf.co/Brucamian/70-qwen15-55-R
| { | |
| "_name_or_path": "/data/cambrian-u/ckpt/20251007_mix70960k_SPMD_1_5b_finetune_diffloss_token256_dit5_5_cfg0_1_context512_ep1_v6-rescue", | |
| "architectures": [ | |
| "CambrianQwenForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "aux_regression": false, | |
| "aux_regression_coef": 1.0, | |
| "bos_token_id": 151643, | |
| "connector_only": true, | |
| "ddt_encoder_depth": 2, | |
| "diff_head_lr": 0.000565, | |
| "diffusion_base_dim": null, | |
| "diffusion_class_dropout_prob": 0.1, | |
| "diffusion_model_channels": 1152, | |
| "diffusion_model_depth": 32, | |
| "diffusion_model_heads": 32, | |
| "diffusion_model_hidden_size": 3072, | |
| "diffusion_model_z_channels": 3072, | |
| "diffusion_norm_stats_path": null, | |
| "diffusion_split_per_token": 256, | |
| "diffusion_timesteps_per_sample": 1, | |
| "eos_token_id": 151645, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "image_aspect_ratio": "square", | |
| "image_position": 35, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "miv_token_len": 0, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": true, | |
| "mm_vision_sampler_lr": null, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -1, | |
| "mm_vision_tower_aux_list": [ | |
| "google/siglip2-so400m-patch14-224" | |
| ], | |
| "mm_vision_tower_aux_token_len_list": [ | |
| 256 | |
| ], | |
| "mm_vision_tower_lr": 2e-06, | |
| "model_type": "cambrian_qwen", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "pretrain_adapter_and_vision_head": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "si_token_len": 729, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": true, | |
| "tokenizer_model_max_length": 512, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.0", | |
| "tune_adapter_and_vision_head": false, | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vision_head": false, | |
| "unfreeze_mm_vision_tower": false, | |
| "use_cache": false, | |
| "use_mm_proj": true, | |
| "use_sliding_window": false, | |
| "vision_coef": 2.0, | |
| "vision_hidden_size": 1152, | |
| "vision_loss": "diffusion-loss", | |
| "vision_loss_mode": "query", | |
| "vision_tower_aux_token_len_list": [ | |
| 256 | |
| ], | |
| "vocab_size": 151667 | |
| } | |