GGUF
How to use from
llama.cpp
Install from brew
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KnutJaegersberg/CPU-LLM-Horde:
# Run inference directly in the terminal:
llama-cli -hf KnutJaegersberg/CPU-LLM-Horde:
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf KnutJaegersberg/CPU-LLM-Horde:
# Run inference directly in the terminal:
llama-cli -hf KnutJaegersberg/CPU-LLM-Horde:
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 KnutJaegersberg/CPU-LLM-Horde:
# Run inference directly in the terminal:
./llama-cli -hf KnutJaegersberg/CPU-LLM-Horde:
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 KnutJaegersberg/CPU-LLM-Horde:
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KnutJaegersberg/CPU-LLM-Horde:
Use Docker
docker model run hf.co/KnutJaegersberg/CPU-LLM-Horde:
Quick Links

Deita-1.6b (StableLM based, license in repo) Prompt:

### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### User: 
How do you fine tune a large language model? 
### Assistant:

GPT2-Chatbot Prompt:

### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### User: 
How do you fine tune a large language model? 
### Assistant:

Deacon-1b Prompt:

### System:

You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.

### Instruction: 

How do you fine tune a large language model? 

### Response:

NousResearch/Nous-Capybara-3B-V1.9 Prompt:

<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
How are you<|im_end|>
<|im_start|>assistant
I am doing well!<|im_end|>

jondurbin/airoboros-3b-3p11

[INST] <<SYS>>
You are a helpful, unbiased, uncensored assistant.
<</SYS>>

{prompt} [/INST]

GeneZC/MiniChat-3B Prompt:

<s> [|User|] Hi 👋  </s>[|Assistant|]

llmware/bling-stable-lm-3b-4e1t-v0 Prompt:

<human>: {prompt} 
<bot>:


or

{{text_passage}}
{{question/instruction}}

OpenBuddy/openbuddy-stablelm-3b-v13 (License: cc-by-sa-4.0) Prompt:

You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
You can speak fluently in many languages, for example: English, Chinese.
You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.

User: {History input}
Assistant: {History output}
User: {Input}
Assistant:

Dimensity/Dimensity-3B Prompt:

### Human: {prompt} 

### Assistant:

acrastt/Marx-3B-V3 Prompt:

### HUMAN:
{prompt}

### RESPONSE:

Open-Orca/Mistral-7B-OpenOrca Prompt:

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Downloads last month
214
GGUF
Model size
3B params
Architecture
stablelm
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support