Text Generation
MLX
Safetensors
bailing_hybrid
Mixture of Experts
mixture-of-experts
hybrid-attention
mla
lightning-attention
mxfp4
osaurus
bailing
ling
apple-silicon
conversational
custom_code
Instructions to use OsaurusAI/Ling-2.6-flash-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/Ling-2.6-flash-MXFP4 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("OsaurusAI/Ling-2.6-flash-MXFP4") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Pi new
How to use OsaurusAI/Ling-2.6-flash-MXFP4 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "OsaurusAI/Ling-2.6-flash-MXFP4"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "OsaurusAI/Ling-2.6-flash-MXFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use OsaurusAI/Ling-2.6-flash-MXFP4 with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "OsaurusAI/Ling-2.6-flash-MXFP4"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default OsaurusAI/Ling-2.6-flash-MXFP4
Run Hermes
hermes
- MLX LM
How to use OsaurusAI/Ling-2.6-flash-MXFP4 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "OsaurusAI/Ling-2.6-flash-MXFP4"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "OsaurusAI/Ling-2.6-flash-MXFP4" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OsaurusAI/Ling-2.6-flash-MXFP4", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "BailingMoeV2_5ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_bailing_moe_v2_5.BailingMoeV2_5Config", | |
| "AutoModel": "modeling_bailing_moe_v2_5.BailingMoeV2_5Model", | |
| "AutoModelForCausalLM": "modeling_bailing_moe_v2_5.BailingMoeV2_5ForCausalLM" | |
| }, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 156895, | |
| "first_k_dense_replace": 1, | |
| "group_norm_size": 4, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "kv_lora_rank": 512, | |
| "layer_group_size": 8, | |
| "linear_silu": false, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 20, | |
| "moe_intermediate_size": 1024, | |
| "moe_router_enable_expert_bias": true, | |
| "moe_shared_expert_intermediate_size": 1024, | |
| "mtp_loss_scaling_factor": 0, | |
| "n_group": 8, | |
| "num_attention_heads": 32, | |
| "num_experts": 256, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "num_kv_heads_for_linear_attn": 32, | |
| "num_nextn_predict_layers": 1, | |
| "num_shared_experts": 1, | |
| "output_dropout": 0.0, | |
| "output_router_logits": false, | |
| "pad_token_id": 156892, | |
| "partial_rotary_factor": 0.5, | |
| "q_lora_rank": 1536, | |
| "qk_head_dim": 192, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": null, | |
| "rope_theta": 6000000, | |
| "rotary_dim": 64, | |
| "routed_scaling_factor": 2.5, | |
| "router_dtype": "fp32", | |
| "score_function": "sigmoid", | |
| "scoring_func": "sigmoid", | |
| "seq_aux": true, | |
| "tie_word_embeddings": false, | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "transformers_version": "4.56.2", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "use_qkv_bias": false, | |
| "v_head_dim": 128, | |
| "vocab_size": 157184, | |
| "model_type": "bailing_hybrid", | |
| "torch_dtype": "bfloat16", | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 32, | |
| "mode": "affine" | |
| }, | |
| "weight_format": "mxfp4" | |
| } |