Instructions to use OsaurusAI/Ling-2.6-flash-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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 Settings
LM Studio

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"}
     ]
   }'

Osaurus-AI commited on 29 days ago

Commit

8cb8b5d

verified ·

1 Parent(s): 70b2d41

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +74 -0

config.json ADDED Viewed

	@@ -0,0 +1,74 @@

+{
+  "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"
+}