Token Classification
GGUF
Safetensors
Chinese
input-method
zhuyin
bopomofo
traditional-chinese
ternary
bitnet
Instructions to use Luigi/sloth-ime-models 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 Luigi/sloth-ime-models 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 Luigi/sloth-ime-models # Run inference directly in the terminal: llama cli -hf Luigi/sloth-ime-models
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Luigi/sloth-ime-models # Run inference directly in the terminal: llama cli -hf Luigi/sloth-ime-models
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 Luigi/sloth-ime-models # Run inference directly in the terminal: ./llama-cli -hf Luigi/sloth-ime-models
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 Luigi/sloth-ime-models # Run inference directly in the terminal: ./build/bin/llama-cli -hf Luigi/sloth-ime-models
Use Docker
docker model run hf.co/Luigi/sloth-ime-models
- LM Studio
- Jan
- Ollama
How to use Luigi/sloth-ime-models with Ollama:
ollama run hf.co/Luigi/sloth-ime-models
- Unsloth Desktop
- Docker Model Runner
How to use Luigi/sloth-ime-models with Docker Model Runner:
docker model run hf.co/Luigi/sloth-ime-models
- Lemonade
How to use Luigi/sloth-ime-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Luigi/sloth-ime-models
Run and chat with the model
lemonade run user.sloth-ime-models-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
12M weights: 12m/roles.json
Browse files- 12m/roles.json +208 -0
12m/roles.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embed.weight": "fp",
|
| 3 |
+
"embed_norm.w": "fp",
|
| 4 |
+
"blocks.0.n1.w": "fp",
|
| 5 |
+
"blocks.0.attn.q.weight": "fp",
|
| 6 |
+
"blocks.0.attn.k.weight": "fp",
|
| 7 |
+
"blocks.0.attn.v.weight": "fp",
|
| 8 |
+
"blocks.0.attn.o.weight": "fp",
|
| 9 |
+
"blocks.0.attn.qn.w": "fp",
|
| 10 |
+
"blocks.0.attn.kn.w": "fp",
|
| 11 |
+
"blocks.0.n2.w": "fp",
|
| 12 |
+
"blocks.0.ffn.w1.weight": "fp",
|
| 13 |
+
"blocks.0.ffn.w3.weight": "fp",
|
| 14 |
+
"blocks.0.ffn.w2.weight": "fp",
|
| 15 |
+
"blocks.1.n1.w": "fp",
|
| 16 |
+
"blocks.1.attn.q.weight": "ternary",
|
| 17 |
+
"blocks.1.attn.q.pre.w": "fp",
|
| 18 |
+
"blocks.1.attn.k.weight": "ternary",
|
| 19 |
+
"blocks.1.attn.k.pre.w": "fp",
|
| 20 |
+
"blocks.1.attn.v.weight": "ternary",
|
| 21 |
+
"blocks.1.attn.v.pre.w": "fp",
|
| 22 |
+
"blocks.1.attn.o.weight": "ternary",
|
| 23 |
+
"blocks.1.attn.o.pre.w": "fp",
|
| 24 |
+
"blocks.1.attn.qn.w": "fp",
|
| 25 |
+
"blocks.1.attn.kn.w": "fp",
|
| 26 |
+
"blocks.1.n2.w": "fp",
|
| 27 |
+
"blocks.1.ffn.w1.weight": "ternary",
|
| 28 |
+
"blocks.1.ffn.w1.pre.w": "fp",
|
| 29 |
+
"blocks.1.ffn.w3.weight": "ternary",
|
| 30 |
+
"blocks.1.ffn.w3.pre.w": "fp",
|
| 31 |
+
"blocks.1.ffn.w2.weight": "ternary",
|
| 32 |
+
"blocks.1.ffn.w2.pre.w": "fp",
|
| 33 |
+
"blocks.2.n1.w": "fp",
|
| 34 |
+
"blocks.2.attn.q.weight": "ternary",
|
| 35 |
+
"blocks.2.attn.q.pre.w": "fp",
|
| 36 |
+
"blocks.2.attn.k.weight": "ternary",
|
| 37 |
+
"blocks.2.attn.k.pre.w": "fp",
|
| 38 |
+
"blocks.2.attn.v.weight": "ternary",
|
| 39 |
+
"blocks.2.attn.v.pre.w": "fp",
|
| 40 |
+
"blocks.2.attn.o.weight": "ternary",
|
| 41 |
+
"blocks.2.attn.o.pre.w": "fp",
|
| 42 |
+
"blocks.2.attn.qn.w": "fp",
|
| 43 |
+
"blocks.2.attn.kn.w": "fp",
|
| 44 |
+
"blocks.2.n2.w": "fp",
|
| 45 |
+
"blocks.2.ffn.w1.weight": "ternary",
|
| 46 |
+
"blocks.2.ffn.w1.pre.w": "fp",
|
| 47 |
+
"blocks.2.ffn.w3.weight": "ternary",
|
| 48 |
+
"blocks.2.ffn.w3.pre.w": "fp",
|
| 49 |
+
"blocks.2.ffn.w2.weight": "ternary",
|
| 50 |
+
"blocks.2.ffn.w2.pre.w": "fp",
|
| 51 |
+
"blocks.3.n1.w": "fp",
|
| 52 |
+
"blocks.3.attn.q.weight": "ternary",
|
| 53 |
+
"blocks.3.attn.q.pre.w": "fp",
|
| 54 |
+
"blocks.3.attn.k.weight": "ternary",
|
| 55 |
+
"blocks.3.attn.k.pre.w": "fp",
|
| 56 |
+
"blocks.3.attn.v.weight": "ternary",
|
| 57 |
+
"blocks.3.attn.v.pre.w": "fp",
|
| 58 |
+
"blocks.3.attn.o.weight": "ternary",
|
| 59 |
+
"blocks.3.attn.o.pre.w": "fp",
|
| 60 |
+
"blocks.3.attn.qn.w": "fp",
|
| 61 |
+
"blocks.3.attn.kn.w": "fp",
|
| 62 |
+
"blocks.3.n2.w": "fp",
|
| 63 |
+
"blocks.3.ffn.w1.weight": "ternary",
|
| 64 |
+
"blocks.3.ffn.w1.pre.w": "fp",
|
| 65 |
+
"blocks.3.ffn.w3.weight": "ternary",
|
| 66 |
+
"blocks.3.ffn.w3.pre.w": "fp",
|
| 67 |
+
"blocks.3.ffn.w2.weight": "ternary",
|
| 68 |
+
"blocks.3.ffn.w2.pre.w": "fp",
|
| 69 |
+
"blocks.4.n1.w": "fp",
|
| 70 |
+
"blocks.4.attn.q.weight": "ternary",
|
| 71 |
+
"blocks.4.attn.q.pre.w": "fp",
|
| 72 |
+
"blocks.4.attn.k.weight": "ternary",
|
| 73 |
+
"blocks.4.attn.k.pre.w": "fp",
|
| 74 |
+
"blocks.4.attn.v.weight": "ternary",
|
| 75 |
+
"blocks.4.attn.v.pre.w": "fp",
|
| 76 |
+
"blocks.4.attn.o.weight": "ternary",
|
| 77 |
+
"blocks.4.attn.o.pre.w": "fp",
|
| 78 |
+
"blocks.4.attn.qn.w": "fp",
|
| 79 |
+
"blocks.4.attn.kn.w": "fp",
|
| 80 |
+
"blocks.4.n2.w": "fp",
|
| 81 |
+
"blocks.4.ffn.w1.weight": "ternary",
|
| 82 |
+
"blocks.4.ffn.w1.pre.w": "fp",
|
| 83 |
+
"blocks.4.ffn.w3.weight": "ternary",
|
| 84 |
+
"blocks.4.ffn.w3.pre.w": "fp",
|
| 85 |
+
"blocks.4.ffn.w2.weight": "ternary",
|
| 86 |
+
"blocks.4.ffn.w2.pre.w": "fp",
|
| 87 |
+
"blocks.5.n1.w": "fp",
|
| 88 |
+
"blocks.5.attn.q.weight": "ternary",
|
| 89 |
+
"blocks.5.attn.q.pre.w": "fp",
|
| 90 |
+
"blocks.5.attn.k.weight": "ternary",
|
| 91 |
+
"blocks.5.attn.k.pre.w": "fp",
|
| 92 |
+
"blocks.5.attn.v.weight": "ternary",
|
| 93 |
+
"blocks.5.attn.v.pre.w": "fp",
|
| 94 |
+
"blocks.5.attn.o.weight": "ternary",
|
| 95 |
+
"blocks.5.attn.o.pre.w": "fp",
|
| 96 |
+
"blocks.5.attn.qn.w": "fp",
|
| 97 |
+
"blocks.5.attn.kn.w": "fp",
|
| 98 |
+
"blocks.5.n2.w": "fp",
|
| 99 |
+
"blocks.5.ffn.w1.weight": "ternary",
|
| 100 |
+
"blocks.5.ffn.w1.pre.w": "fp",
|
| 101 |
+
"blocks.5.ffn.w3.weight": "ternary",
|
| 102 |
+
"blocks.5.ffn.w3.pre.w": "fp",
|
| 103 |
+
"blocks.5.ffn.w2.weight": "ternary",
|
| 104 |
+
"blocks.5.ffn.w2.pre.w": "fp",
|
| 105 |
+
"blocks.6.n1.w": "fp",
|
| 106 |
+
"blocks.6.attn.q.weight": "ternary",
|
| 107 |
+
"blocks.6.attn.q.pre.w": "fp",
|
| 108 |
+
"blocks.6.attn.k.weight": "ternary",
|
| 109 |
+
"blocks.6.attn.k.pre.w": "fp",
|
| 110 |
+
"blocks.6.attn.v.weight": "ternary",
|
| 111 |
+
"blocks.6.attn.v.pre.w": "fp",
|
| 112 |
+
"blocks.6.attn.o.weight": "ternary",
|
| 113 |
+
"blocks.6.attn.o.pre.w": "fp",
|
| 114 |
+
"blocks.6.attn.qn.w": "fp",
|
| 115 |
+
"blocks.6.attn.kn.w": "fp",
|
| 116 |
+
"blocks.6.n2.w": "fp",
|
| 117 |
+
"blocks.6.ffn.w1.weight": "ternary",
|
| 118 |
+
"blocks.6.ffn.w1.pre.w": "fp",
|
| 119 |
+
"blocks.6.ffn.w3.weight": "ternary",
|
| 120 |
+
"blocks.6.ffn.w3.pre.w": "fp",
|
| 121 |
+
"blocks.6.ffn.w2.weight": "ternary",
|
| 122 |
+
"blocks.6.ffn.w2.pre.w": "fp",
|
| 123 |
+
"blocks.7.n1.w": "fp",
|
| 124 |
+
"blocks.7.attn.q.weight": "ternary",
|
| 125 |
+
"blocks.7.attn.q.pre.w": "fp",
|
| 126 |
+
"blocks.7.attn.k.weight": "ternary",
|
| 127 |
+
"blocks.7.attn.k.pre.w": "fp",
|
| 128 |
+
"blocks.7.attn.v.weight": "ternary",
|
| 129 |
+
"blocks.7.attn.v.pre.w": "fp",
|
| 130 |
+
"blocks.7.attn.o.weight": "ternary",
|
| 131 |
+
"blocks.7.attn.o.pre.w": "fp",
|
| 132 |
+
"blocks.7.attn.qn.w": "fp",
|
| 133 |
+
"blocks.7.attn.kn.w": "fp",
|
| 134 |
+
"blocks.7.n2.w": "fp",
|
| 135 |
+
"blocks.7.ffn.w1.weight": "ternary",
|
| 136 |
+
"blocks.7.ffn.w1.pre.w": "fp",
|
| 137 |
+
"blocks.7.ffn.w3.weight": "ternary",
|
| 138 |
+
"blocks.7.ffn.w3.pre.w": "fp",
|
| 139 |
+
"blocks.7.ffn.w2.weight": "ternary",
|
| 140 |
+
"blocks.7.ffn.w2.pre.w": "fp",
|
| 141 |
+
"blocks.8.n1.w": "fp",
|
| 142 |
+
"blocks.8.attn.q.weight": "ternary",
|
| 143 |
+
"blocks.8.attn.q.pre.w": "fp",
|
| 144 |
+
"blocks.8.attn.k.weight": "ternary",
|
| 145 |
+
"blocks.8.attn.k.pre.w": "fp",
|
| 146 |
+
"blocks.8.attn.v.weight": "ternary",
|
| 147 |
+
"blocks.8.attn.v.pre.w": "fp",
|
| 148 |
+
"blocks.8.attn.o.weight": "ternary",
|
| 149 |
+
"blocks.8.attn.o.pre.w": "fp",
|
| 150 |
+
"blocks.8.attn.qn.w": "fp",
|
| 151 |
+
"blocks.8.attn.kn.w": "fp",
|
| 152 |
+
"blocks.8.n2.w": "fp",
|
| 153 |
+
"blocks.8.ffn.w1.weight": "ternary",
|
| 154 |
+
"blocks.8.ffn.w1.pre.w": "fp",
|
| 155 |
+
"blocks.8.ffn.w3.weight": "ternary",
|
| 156 |
+
"blocks.8.ffn.w3.pre.w": "fp",
|
| 157 |
+
"blocks.8.ffn.w2.weight": "ternary",
|
| 158 |
+
"blocks.8.ffn.w2.pre.w": "fp",
|
| 159 |
+
"blocks.9.n1.w": "fp",
|
| 160 |
+
"blocks.9.attn.q.weight": "ternary",
|
| 161 |
+
"blocks.9.attn.q.pre.w": "fp",
|
| 162 |
+
"blocks.9.attn.k.weight": "ternary",
|
| 163 |
+
"blocks.9.attn.k.pre.w": "fp",
|
| 164 |
+
"blocks.9.attn.v.weight": "ternary",
|
| 165 |
+
"blocks.9.attn.v.pre.w": "fp",
|
| 166 |
+
"blocks.9.attn.o.weight": "ternary",
|
| 167 |
+
"blocks.9.attn.o.pre.w": "fp",
|
| 168 |
+
"blocks.9.attn.qn.w": "fp",
|
| 169 |
+
"blocks.9.attn.kn.w": "fp",
|
| 170 |
+
"blocks.9.n2.w": "fp",
|
| 171 |
+
"blocks.9.ffn.w1.weight": "ternary",
|
| 172 |
+
"blocks.9.ffn.w1.pre.w": "fp",
|
| 173 |
+
"blocks.9.ffn.w3.weight": "ternary",
|
| 174 |
+
"blocks.9.ffn.w3.pre.w": "fp",
|
| 175 |
+
"blocks.9.ffn.w2.weight": "ternary",
|
| 176 |
+
"blocks.9.ffn.w2.pre.w": "fp",
|
| 177 |
+
"blocks.10.n1.w": "fp",
|
| 178 |
+
"blocks.10.attn.q.weight": "ternary",
|
| 179 |
+
"blocks.10.attn.q.pre.w": "fp",
|
| 180 |
+
"blocks.10.attn.k.weight": "ternary",
|
| 181 |
+
"blocks.10.attn.k.pre.w": "fp",
|
| 182 |
+
"blocks.10.attn.v.weight": "ternary",
|
| 183 |
+
"blocks.10.attn.v.pre.w": "fp",
|
| 184 |
+
"blocks.10.attn.o.weight": "ternary",
|
| 185 |
+
"blocks.10.attn.o.pre.w": "fp",
|
| 186 |
+
"blocks.10.attn.qn.w": "fp",
|
| 187 |
+
"blocks.10.attn.kn.w": "fp",
|
| 188 |
+
"blocks.10.n2.w": "fp",
|
| 189 |
+
"blocks.10.ffn.w1.weight": "ternary",
|
| 190 |
+
"blocks.10.ffn.w1.pre.w": "fp",
|
| 191 |
+
"blocks.10.ffn.w3.weight": "ternary",
|
| 192 |
+
"blocks.10.ffn.w3.pre.w": "fp",
|
| 193 |
+
"blocks.10.ffn.w2.weight": "ternary",
|
| 194 |
+
"blocks.10.ffn.w2.pre.w": "fp",
|
| 195 |
+
"blocks.11.n1.w": "fp",
|
| 196 |
+
"blocks.11.attn.q.weight": "fp",
|
| 197 |
+
"blocks.11.attn.k.weight": "fp",
|
| 198 |
+
"blocks.11.attn.v.weight": "fp",
|
| 199 |
+
"blocks.11.attn.o.weight": "fp",
|
| 200 |
+
"blocks.11.attn.qn.w": "fp",
|
| 201 |
+
"blocks.11.attn.kn.w": "fp",
|
| 202 |
+
"blocks.11.n2.w": "fp",
|
| 203 |
+
"blocks.11.ffn.w1.weight": "fp",
|
| 204 |
+
"blocks.11.ffn.w3.weight": "fp",
|
| 205 |
+
"blocks.11.ffn.w2.weight": "fp",
|
| 206 |
+
"norm.w": "fp",
|
| 207 |
+
"head.weight": "fp"
|
| 208 |
+
}
|