Instructions to use leafspark/wikichat-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/wikichat-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="leafspark/wikichat-v2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("leafspark/wikichat-v2", dtype="auto")

llama-cpp-python

How to use leafspark/wikichat-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="leafspark/wikichat-v2",
	filename="chk-wikichat2-384x32-16-test.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use leafspark/wikichat-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf leafspark/wikichat-v2:F32
# Run inference directly in the terminal:
llama-cli -hf leafspark/wikichat-v2:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf leafspark/wikichat-v2:F32
# Run inference directly in the terminal:
llama-cli -hf leafspark/wikichat-v2:F32

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 leafspark/wikichat-v2:F32
# Run inference directly in the terminal:
./llama-cli -hf leafspark/wikichat-v2:F32

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 leafspark/wikichat-v2:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf leafspark/wikichat-v2:F32

Use Docker

docker model run hf.co/leafspark/wikichat-v2:F32

LM Studio
Jan

vLLM

How to use leafspark/wikichat-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leafspark/wikichat-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/wikichat-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/leafspark/wikichat-v2:F32

SGLang

How to use leafspark/wikichat-v2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "leafspark/wikichat-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/wikichat-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "leafspark/wikichat-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/wikichat-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use leafspark/wikichat-v2 with Ollama:
```
ollama run hf.co/leafspark/wikichat-v2:F32
```

Unsloth Studio

How to use leafspark/wikichat-v2 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 leafspark/wikichat-v2 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 leafspark/wikichat-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for leafspark/wikichat-v2 to start chatting

Docker Model Runner
How to use leafspark/wikichat-v2 with Docker Model Runner:
```
docker model run hf.co/leafspark/wikichat-v2:F32
```

Lemonade

How to use leafspark/wikichat-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull leafspark/wikichat-v2:F32

Run and chat with the model

lemonade run user.wikichat-v2-F32

List all available models

lemonade list

leafspark commited on Apr 24, 2024

Commit

5f7b78a

verified ·

1 Parent(s): 90deb40

Update README.md

Browse files

Files changed (1) hide show

README.md +54 -0

README.md CHANGED Viewed

@@ -1,3 +1,57 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
+datasets:
+- HuggingFaceTB/cosmopedia
+- databricks/databricks-dolly-15k
+- Open-Orca/OpenOrca
+language:
+- en
+metrics:
+- accuracy
+library_name: transformers
+pipeline_tag: text-generation
 ---
+# WikiChat-v0.2
+Training in progress model to have conversations.
+The GGUFs uploaded are full FP32 precision.
+Using OpenOrca GPT-4 data + cosmopedia for some extra data + dolly15k for instruct
+## Model Details:
+- 40M parameters
+- 8 attention heads
+- 32 layers
+- 384 embeddings size
+- 2048/8192 context (please use 4x RoPE scaling)
+## Prompt Format (Alpaca):
+```
+Instruction: {system}
+Input: {prompt}
+Response: {response}
+```
+Please structure your prompts in an instruct format for maximum performance.
+## Training Details:
+- 1x RTX 3070 8GB (Infrencing speed: 80tok/s, full GPU offload)
+- 1x Ryzen 3 3700x
+- 96gb RAM
+- 10 iterations
+- Loss Target = 2.5 to 3.0
+- Approx 30 samples (>0.0001 epoches)
+- Training data = Refer to OpenOrca page
+## Notes:
+The model isn't ready yet; this is to test tokenization of OpenOrca and a balance between training speed and model size
+## Example output:
+```
+User: What is the square root of 4?
+```
+```
+Assistant: The square root of 4 is 2.
+```