Instructions to use ksjpswaroop/CleverOfficeGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ksjpswaroop/CleverOfficeGPT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ksjpswaroop/CleverOfficeGPT",
	filename="cleverOfficeGPT-1.5b-fp16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ksjpswaroop/CleverOfficeGPT with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ksjpswaroop/CleverOfficeGPT
# Run inference directly in the terminal:
llama-cli -hf ksjpswaroop/CleverOfficeGPT

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ksjpswaroop/CleverOfficeGPT
# Run inference directly in the terminal:
llama-cli -hf ksjpswaroop/CleverOfficeGPT

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 ksjpswaroop/CleverOfficeGPT
# Run inference directly in the terminal:
./llama-cli -hf ksjpswaroop/CleverOfficeGPT

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 ksjpswaroop/CleverOfficeGPT
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ksjpswaroop/CleverOfficeGPT

Use Docker

docker model run hf.co/ksjpswaroop/CleverOfficeGPT

LM Studio
Jan
Ollama
How to use ksjpswaroop/CleverOfficeGPT with Ollama:
```
ollama run hf.co/ksjpswaroop/CleverOfficeGPT
```

Unsloth Studio

How to use ksjpswaroop/CleverOfficeGPT 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 ksjpswaroop/CleverOfficeGPT 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 ksjpswaroop/CleverOfficeGPT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ksjpswaroop/CleverOfficeGPT to start chatting

Docker Model Runner
How to use ksjpswaroop/CleverOfficeGPT with Docker Model Runner:
```
docker model run hf.co/ksjpswaroop/CleverOfficeGPT
```

Lemonade

How to use ksjpswaroop/CleverOfficeGPT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ksjpswaroop/CleverOfficeGPT

Run and chat with the model

lemonade run user.CleverOfficeGPT-{{QUANT_TAG}}

List all available models

lemonade list

ksjpswaroop commited on Sep 5, 2024

Commit

5c07efd

verified ·

1 Parent(s): 3ca2fda

Upload 5 files

Browse files

Files changed (5) hide show

.gitattributes +1 -0
cleverOfficeGPT-1.5b-fp16.gguf +3 -0
params +11 -0
system +1 -0
template +6 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+cleverOfficeGPT-1.5b-fp16.gguf filter=lfs diff=lfs merge=lfs -text

cleverOfficeGPT-1.5b-fp16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7555a5804e14d918aadd73518567affcf29fcec23f9a992dd2353fea8d0249
+size 3560413856

params ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+    "num_ctx": 32768,
+    "num_predict": 2048,
+    "stop": [
+        "<|im_end|>",
+        "<|im_start|>"
+    ],
+    "temperature": 0.5,
+    "top_k": 45,
+    "top_p": 0.95
+}

system ADDED Viewed

	@@ -0,0 +1 @@


1	+ You are a clever, unbiased, uncensored, and helpful AI assistant for Office operations.

template ADDED Viewed

	@@ -0,0 +1,6 @@

+{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ .Response }}<|im_end|>