Safetensors
GGUF
qwen3_5_moe
qwen4_exp
mixture-of-experts
hyper-connections
per-layer-embeddings
n-gram-memory
model-compression
research
conversational
Instructions to use logic65/whittle-next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use logic65/whittle-next with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf logic65/whittle-next:F16 # Run inference directly in the terminal: llama cli -hf logic65/whittle-next:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf logic65/whittle-next:F16 # Run inference directly in the terminal: llama cli -hf logic65/whittle-next:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf logic65/whittle-next:F16 # Run inference directly in the terminal: ./llama-cli -hf logic65/whittle-next:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf logic65/whittle-next:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf logic65/whittle-next:F16
Use Docker
docker model run hf.co/logic65/whittle-next:F16
- LM Studio
- Jan
- Ollama
How to use logic65/whittle-next with Ollama:
ollama run hf.co/logic65/whittle-next:F16
- Unsloth Desktop
- Pi
How to use logic65/whittle-next with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf logic65/whittle-next:F16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "logic65/whittle-next:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use logic65/whittle-next with Docker Model Runner:
docker model run hf.co/logic65/whittle-next:F16
- Lemonade
How to use logic65/whittle-next with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull logic65/whittle-next:F16
Run and chat with the model
lemonade run user.whittle-next-F16
List all available models
lemonade list
- Hermes Agent
How to use logic65/whittle-next with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf logic65/whittle-next:F16
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 logic65/whittle-next:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use logic65/whittle-next with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf logic65/whittle-next:F16
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "logic65/whittle-next:F16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Upload config.json with huggingface_hub
Browse files- config.json +201 -0
config.json
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_bias": false,
|
| 3 |
+
"attention_dropout": 0.0,
|
| 4 |
+
"attn_output_gate": true,
|
| 5 |
+
"bos_token_id": 248044,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248044,
|
| 8 |
+
"full_attention_interval": 4,
|
| 9 |
+
"head_dim": 256,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 13056,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"linear_attention",
|
| 16 |
+
"linear_attention",
|
| 17 |
+
"linear_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"full_attention"
|
| 59 |
+
],
|
| 60 |
+
"linear_conv_kernel_dim": 4,
|
| 61 |
+
"linear_key_head_dim": 128,
|
| 62 |
+
"linear_num_key_heads": 16,
|
| 63 |
+
"linear_num_value_heads": 48,
|
| 64 |
+
"linear_value_head_dim": 128,
|
| 65 |
+
"mamba_ssm_dtype": "float32",
|
| 66 |
+
"max_position_embeddings": 262144,
|
| 67 |
+
"model_type": "qwen3_5_moe",
|
| 68 |
+
"mtp_num_hidden_layers": 1,
|
| 69 |
+
"mtp_use_dedicated_embeddings": false,
|
| 70 |
+
"num_attention_heads": 24,
|
| 71 |
+
"num_hidden_layers": 44,
|
| 72 |
+
"num_key_value_heads": 4,
|
| 73 |
+
"output_gate_type": "swish",
|
| 74 |
+
"pad_token_id": null,
|
| 75 |
+
"partial_rotary_factor": 0.25,
|
| 76 |
+
"rms_norm_eps": 1e-06,
|
| 77 |
+
"rope_parameters": {
|
| 78 |
+
"mrope_interleaved": true,
|
| 79 |
+
"mrope_section": [
|
| 80 |
+
11,
|
| 81 |
+
11,
|
| 82 |
+
10
|
| 83 |
+
],
|
| 84 |
+
"partial_rotary_factor": 0.25,
|
| 85 |
+
"rope_theta": 10000000,
|
| 86 |
+
"rope_type": "default"
|
| 87 |
+
},
|
| 88 |
+
"tie_word_embeddings": false,
|
| 89 |
+
"use_cache": true,
|
| 90 |
+
"vocab_size": 248320,
|
| 91 |
+
"torch_dtype": "bfloat16",
|
| 92 |
+
"architectures": [
|
| 93 |
+
"Qwen3_5MoeForCausalLM"
|
| 94 |
+
],
|
| 95 |
+
"num_experts": 67,
|
| 96 |
+
"num_experts_per_tok": 16,
|
| 97 |
+
"moe_intermediate_size": 192,
|
| 98 |
+
"shared_expert_intermediate_size": 192,
|
| 99 |
+
"decoder_sparse_step": 1,
|
| 100 |
+
"norm_topk_prob": true,
|
| 101 |
+
"mlp_only_layers": [],
|
| 102 |
+
"text_config": {
|
| 103 |
+
"attention_bias": false,
|
| 104 |
+
"attention_dropout": 0.0,
|
| 105 |
+
"attn_output_gate": true,
|
| 106 |
+
"bos_token_id": 248044,
|
| 107 |
+
"dtype": "bfloat16",
|
| 108 |
+
"eos_token_id": 248044,
|
| 109 |
+
"full_attention_interval": 4,
|
| 110 |
+
"head_dim": 256,
|
| 111 |
+
"hidden_act": "silu",
|
| 112 |
+
"hidden_size": 5120,
|
| 113 |
+
"initializer_range": 0.02,
|
| 114 |
+
"intermediate_size": 13056,
|
| 115 |
+
"layer_types": [
|
| 116 |
+
"linear_attention",
|
| 117 |
+
"linear_attention",
|
| 118 |
+
"linear_attention",
|
| 119 |
+
"full_attention",
|
| 120 |
+
"linear_attention",
|
| 121 |
+
"linear_attention",
|
| 122 |
+
"linear_attention",
|
| 123 |
+
"full_attention",
|
| 124 |
+
"linear_attention",
|
| 125 |
+
"linear_attention",
|
| 126 |
+
"linear_attention",
|
| 127 |
+
"full_attention",
|
| 128 |
+
"linear_attention",
|
| 129 |
+
"linear_attention",
|
| 130 |
+
"linear_attention",
|
| 131 |
+
"full_attention",
|
| 132 |
+
"linear_attention",
|
| 133 |
+
"linear_attention",
|
| 134 |
+
"linear_attention",
|
| 135 |
+
"full_attention",
|
| 136 |
+
"linear_attention",
|
| 137 |
+
"linear_attention",
|
| 138 |
+
"linear_attention",
|
| 139 |
+
"full_attention",
|
| 140 |
+
"linear_attention",
|
| 141 |
+
"linear_attention",
|
| 142 |
+
"linear_attention",
|
| 143 |
+
"full_attention",
|
| 144 |
+
"linear_attention",
|
| 145 |
+
"linear_attention",
|
| 146 |
+
"linear_attention",
|
| 147 |
+
"full_attention",
|
| 148 |
+
"linear_attention",
|
| 149 |
+
"linear_attention",
|
| 150 |
+
"linear_attention",
|
| 151 |
+
"full_attention",
|
| 152 |
+
"linear_attention",
|
| 153 |
+
"linear_attention",
|
| 154 |
+
"linear_attention",
|
| 155 |
+
"full_attention",
|
| 156 |
+
"linear_attention",
|
| 157 |
+
"linear_attention",
|
| 158 |
+
"linear_attention",
|
| 159 |
+
"full_attention"
|
| 160 |
+
],
|
| 161 |
+
"linear_conv_kernel_dim": 4,
|
| 162 |
+
"linear_key_head_dim": 128,
|
| 163 |
+
"linear_num_key_heads": 16,
|
| 164 |
+
"linear_num_value_heads": 48,
|
| 165 |
+
"linear_value_head_dim": 128,
|
| 166 |
+
"mamba_ssm_dtype": "float32",
|
| 167 |
+
"max_position_embeddings": 262144,
|
| 168 |
+
"model_type": "qwen3_5_moe",
|
| 169 |
+
"mtp_num_hidden_layers": 1,
|
| 170 |
+
"mtp_use_dedicated_embeddings": false,
|
| 171 |
+
"num_attention_heads": 24,
|
| 172 |
+
"num_hidden_layers": 44,
|
| 173 |
+
"num_key_value_heads": 4,
|
| 174 |
+
"output_gate_type": "swish",
|
| 175 |
+
"pad_token_id": null,
|
| 176 |
+
"partial_rotary_factor": 0.25,
|
| 177 |
+
"rms_norm_eps": 1e-06,
|
| 178 |
+
"rope_parameters": {
|
| 179 |
+
"mrope_interleaved": true,
|
| 180 |
+
"mrope_section": [
|
| 181 |
+
11,
|
| 182 |
+
11,
|
| 183 |
+
10
|
| 184 |
+
],
|
| 185 |
+
"partial_rotary_factor": 0.25,
|
| 186 |
+
"rope_theta": 10000000,
|
| 187 |
+
"rope_type": "default"
|
| 188 |
+
},
|
| 189 |
+
"tie_word_embeddings": false,
|
| 190 |
+
"use_cache": true,
|
| 191 |
+
"vocab_size": 248320,
|
| 192 |
+
"torch_dtype": "bfloat16",
|
| 193 |
+
"num_experts": 67,
|
| 194 |
+
"num_experts_per_tok": 16,
|
| 195 |
+
"moe_intermediate_size": 192,
|
| 196 |
+
"shared_expert_intermediate_size": 192,
|
| 197 |
+
"decoder_sparse_step": 1,
|
| 198 |
+
"norm_topk_prob": true,
|
| 199 |
+
"mlp_only_layers": []
|
| 200 |
+
}
|
| 201 |
+
}
|