Text Generation
GGUF
English
llama.cpp
llama-cpp
qwen3.5
saber
refusal-shaping
abliteration
imatrix
conversational
Instructions to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF", filename="Ornstein-Hermes-3.6-27b-SABER-IQ2_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
Use Docker
docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
- Ollama
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Ollama:
ollama run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
- Unsloth Studio
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF to start chatting
- Pi
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
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 GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Docker Model Runner:
docker model run hf.co/GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
- Lemonade
How to use GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull GestaltLabs/Ornstein-Hermes-3.6-27B-SABER-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Ornstein-Hermes-3.6-27B-SABER-GGUF-Q4_K_M
List all available models
lemonade list
Publish GGUF model card and release image
Browse files- kld_eval.json +193 -0
kld_eval.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mean_kld": 11.221576690673828,
|
| 3 |
+
"median_kld": 11.258872032165527,
|
| 4 |
+
"max_kld": 12.6110258102417,
|
| 5 |
+
"n_prompts": 149,
|
| 6 |
+
"n_tokens_scored": 3347,
|
| 7 |
+
"per_prompt_kld": [
|
| 8 |
+
11.088411331176758,
|
| 9 |
+
11.219141006469727,
|
| 10 |
+
11.621265411376953,
|
| 11 |
+
12.6110258102417,
|
| 12 |
+
10.68524169921875,
|
| 13 |
+
11.140201568603516,
|
| 14 |
+
11.520444869995117,
|
| 15 |
+
10.960616111755371,
|
| 16 |
+
10.777615547180176,
|
| 17 |
+
11.410308837890625,
|
| 18 |
+
11.258872032165527,
|
| 19 |
+
11.032586097717285,
|
| 20 |
+
11.258166313171387,
|
| 21 |
+
11.031803131103516,
|
| 22 |
+
10.884684562683105,
|
| 23 |
+
11.323512077331543,
|
| 24 |
+
11.020181655883789,
|
| 25 |
+
10.976235389709473,
|
| 26 |
+
11.299304962158203,
|
| 27 |
+
10.990053176879883,
|
| 28 |
+
11.231590270996094,
|
| 29 |
+
11.41917610168457,
|
| 30 |
+
10.79571533203125,
|
| 31 |
+
11.284976959228516,
|
| 32 |
+
10.963725090026855,
|
| 33 |
+
11.233430862426758,
|
| 34 |
+
10.440763473510742,
|
| 35 |
+
11.064282417297363,
|
| 36 |
+
10.752723693847656,
|
| 37 |
+
11.36770248413086,
|
| 38 |
+
11.30264663696289,
|
| 39 |
+
11.03974723815918,
|
| 40 |
+
10.517435073852539,
|
| 41 |
+
11.509033203125,
|
| 42 |
+
12.110434532165527,
|
| 43 |
+
11.292105674743652,
|
| 44 |
+
11.4240140914917,
|
| 45 |
+
11.408430099487305,
|
| 46 |
+
10.715821266174316,
|
| 47 |
+
11.311901092529297,
|
| 48 |
+
11.211177825927734,
|
| 49 |
+
11.86925220489502,
|
| 50 |
+
11.532733917236328,
|
| 51 |
+
11.234238624572754,
|
| 52 |
+
10.591565132141113,
|
| 53 |
+
11.428839683532715,
|
| 54 |
+
11.287821769714355,
|
| 55 |
+
10.952550888061523,
|
| 56 |
+
11.418365478515625,
|
| 57 |
+
11.173288345336914,
|
| 58 |
+
11.255884170532227,
|
| 59 |
+
11.680008888244629,
|
| 60 |
+
11.859249114990234,
|
| 61 |
+
12.274761199951172,
|
| 62 |
+
10.865030288696289,
|
| 63 |
+
12.32365608215332,
|
| 64 |
+
10.69661808013916,
|
| 65 |
+
11.384410858154297,
|
| 66 |
+
10.380537033081055,
|
| 67 |
+
11.791696548461914,
|
| 68 |
+
11.39106273651123,
|
| 69 |
+
10.19461441040039,
|
| 70 |
+
11.505685806274414,
|
| 71 |
+
12.090253829956055,
|
| 72 |
+
9.8773832321167,
|
| 73 |
+
11.96424388885498,
|
| 74 |
+
10.161200523376465,
|
| 75 |
+
12.014456748962402,
|
| 76 |
+
12.1090726852417,
|
| 77 |
+
10.899617195129395,
|
| 78 |
+
11.430069923400879,
|
| 79 |
+
9.983293533325195,
|
| 80 |
+
9.216832160949707,
|
| 81 |
+
9.708819389343262,
|
| 82 |
+
11.234479904174805,
|
| 83 |
+
10.906900405883789,
|
| 84 |
+
10.548215866088867,
|
| 85 |
+
10.039212226867676,
|
| 86 |
+
10.290567398071289,
|
| 87 |
+
11.07107162475586,
|
| 88 |
+
10.919650077819824,
|
| 89 |
+
11.652368545532227,
|
| 90 |
+
10.552318572998047,
|
| 91 |
+
11.144087791442871,
|
| 92 |
+
11.851831436157227,
|
| 93 |
+
11.722827911376953,
|
| 94 |
+
9.836979866027832,
|
| 95 |
+
10.675317764282227,
|
| 96 |
+
10.583539009094238,
|
| 97 |
+
11.40699291229248,
|
| 98 |
+
11.25241756439209,
|
| 99 |
+
10.923582077026367,
|
| 100 |
+
11.38624382019043,
|
| 101 |
+
11.9610595703125,
|
| 102 |
+
11.972453117370605,
|
| 103 |
+
10.899657249450684,
|
| 104 |
+
11.808647155761719,
|
| 105 |
+
11.49081802368164,
|
| 106 |
+
11.404881477355957,
|
| 107 |
+
11.787206649780273,
|
| 108 |
+
11.943115234375,
|
| 109 |
+
11.409533500671387,
|
| 110 |
+
11.602027893066406,
|
| 111 |
+
11.717741012573242,
|
| 112 |
+
11.358838081359863,
|
| 113 |
+
11.941396713256836,
|
| 114 |
+
11.313089370727539,
|
| 115 |
+
11.705666542053223,
|
| 116 |
+
10.940914154052734,
|
| 117 |
+
11.295038223266602,
|
| 118 |
+
11.552539825439453,
|
| 119 |
+
11.37530517578125,
|
| 120 |
+
10.844785690307617,
|
| 121 |
+
12.011767387390137,
|
| 122 |
+
11.631556510925293,
|
| 123 |
+
11.210546493530273,
|
| 124 |
+
11.712545394897461,
|
| 125 |
+
11.320769309997559,
|
| 126 |
+
11.7811279296875,
|
| 127 |
+
11.945680618286133,
|
| 128 |
+
11.9591064453125,
|
| 129 |
+
12.281725883483887,
|
| 130 |
+
12.5641508102417,
|
| 131 |
+
10.741057395935059,
|
| 132 |
+
12.088197708129883,
|
| 133 |
+
11.727904319763184,
|
| 134 |
+
11.99649715423584,
|
| 135 |
+
10.931884765625,
|
| 136 |
+
11.179726600646973,
|
| 137 |
+
11.35831069946289,
|
| 138 |
+
10.735390663146973,
|
| 139 |
+
10.928388595581055,
|
| 140 |
+
11.275750160217285,
|
| 141 |
+
11.84463119506836,
|
| 142 |
+
9.995723724365234,
|
| 143 |
+
10.815656661987305,
|
| 144 |
+
11.17290210723877,
|
| 145 |
+
10.637384414672852,
|
| 146 |
+
11.521681785583496,
|
| 147 |
+
10.465771675109863,
|
| 148 |
+
11.291878700256348,
|
| 149 |
+
10.575798034667969,
|
| 150 |
+
11.112957000732422,
|
| 151 |
+
10.597251892089844,
|
| 152 |
+
10.86774730682373,
|
| 153 |
+
10.486213684082031,
|
| 154 |
+
10.766515731811523,
|
| 155 |
+
11.25387954711914,
|
| 156 |
+
11.849738121032715
|
| 157 |
+
],
|
| 158 |
+
"per_category_kld": {
|
| 159 |
+
"harmless": 11.200447082519531,
|
| 160 |
+
"arithmetic": 11.349655151367188,
|
| 161 |
+
"logic": 10.713399887084961,
|
| 162 |
+
"code": 11.511313438415527,
|
| 163 |
+
"instruction": 11.607595443725586,
|
| 164 |
+
"factual": 10.977678298950195
|
| 165 |
+
},
|
| 166 |
+
"top_divergent": [
|
| 167 |
+
{
|
| 168 |
+
"prompt": "Explain the theory of general relativity in simple terms.",
|
| 169 |
+
"category": "harmless",
|
| 170 |
+
"kld": 12.6110258102417
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"prompt": "Explain the concept of recursion in exactly 2 sentences.",
|
| 174 |
+
"category": "instruction",
|
| 175 |
+
"kld": 12.5641508102417
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"prompt": "If a shirt costs $24 after a 20% discount, what was the original price?",
|
| 179 |
+
"category": "arithmetic",
|
| 180 |
+
"kld": 12.32365608215332
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"prompt": "List the first 10 elements of the periodic table with their symbols.",
|
| 184 |
+
"category": "instruction",
|
| 185 |
+
"kld": 12.281725883483887
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"prompt": "A train travels 60 mph for 2.5 hours. How far does it go?",
|
| 189 |
+
"category": "arithmetic",
|
| 190 |
+
"kld": 12.274761199951172
|
| 191 |
+
}
|
| 192 |
+
]
|
| 193 |
+
}
|