Instructions to use legionarius/watt-tool-8B-GGUF 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 legionarius/watt-tool-8B-GGUF 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 legionarius/watt-tool-8B-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf legionarius/watt-tool-8B-GGUF:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf legionarius/watt-tool-8B-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf legionarius/watt-tool-8B-GGUF:Q5_K_M
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 legionarius/watt-tool-8B-GGUF:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf legionarius/watt-tool-8B-GGUF:Q5_K_M
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 legionarius/watt-tool-8B-GGUF:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf legionarius/watt-tool-8B-GGUF:Q5_K_M
Use Docker
docker model run hf.co/legionarius/watt-tool-8B-GGUF:Q5_K_M
- LM Studio
- Jan
- Ollama
How to use legionarius/watt-tool-8B-GGUF with Ollama:
ollama run hf.co/legionarius/watt-tool-8B-GGUF:Q5_K_M
- Unsloth Desktop
- Docker Model Runner
How to use legionarius/watt-tool-8B-GGUF with Docker Model Runner:
docker model run hf.co/legionarius/watt-tool-8B-GGUF:Q5_K_M
- Lemonade
How to use legionarius/watt-tool-8B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull legionarius/watt-tool-8B-GGUF:Q5_K_M
Run and chat with the model
lemonade run user.watt-tool-8B-GGUF-Q5_K_M
List all available models
lemonade list
- Atomic Chat
I really want a default file :(
Browse files- config.json +8 -8
config.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"architectures": ["LlamaForCausalLM"],
|
| 3 |
"attention_bias": false,
|
| 4 |
"attention_dropout": 0.0,
|
|
@@ -11,7 +18,6 @@
|
|
| 11 |
"intermediate_size": 14336,
|
| 12 |
"max_position_embeddings": 131072,
|
| 13 |
"mlp_bias": false,
|
| 14 |
-
"model_type": "llama",
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
|
@@ -29,11 +35,5 @@
|
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.45.2",
|
| 31 |
"use_cache": true,
|
| 32 |
-
"vocab_size": 128256
|
| 33 |
-
"default_gguf_file": "watt-tool-8B-Q4_K_M.gguf",
|
| 34 |
-
"quantization": {
|
| 35 |
-
"method": "gguf",
|
| 36 |
-
"bits": 4,
|
| 37 |
-
"format": "GGUF"
|
| 38 |
-
}
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_type": "llama",
|
| 3 |
+
"quantization": {
|
| 4 |
+
"method": "gguf",
|
| 5 |
+
"bits": 4,
|
| 6 |
+
"format": "GGUF"
|
| 7 |
+
},
|
| 8 |
+
"default_model_file": "watt-tool-8b-q4_k_m.gguf",
|
| 9 |
"architectures": ["LlamaForCausalLM"],
|
| 10 |
"attention_bias": false,
|
| 11 |
"attention_dropout": 0.0,
|
|
|
|
| 18 |
"intermediate_size": 14336,
|
| 19 |
"max_position_embeddings": 131072,
|
| 20 |
"mlp_bias": false,
|
|
|
|
| 21 |
"num_attention_heads": 32,
|
| 22 |
"num_hidden_layers": 32,
|
| 23 |
"num_key_value_heads": 8,
|
|
|
|
| 35 |
"torch_dtype": "bfloat16",
|
| 36 |
"transformers_version": "4.45.2",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 128256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
}
|