Instructions to use kat33/pulchra-c32k-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kat33/pulchra-c32k-all with Transformers:

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

pipe = pipeline("text-generation", model="kat33/pulchra-c32k-all")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kat33/pulchra-c32k-all")
model = AutoModelForCausalLM.from_pretrained("kat33/pulchra-c32k-all", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kat33/pulchra-c32k-all 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 kat33/pulchra-c32k-all:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kat33/pulchra-c32k-all:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kat33/pulchra-c32k-all:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kat33/pulchra-c32k-all: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 kat33/pulchra-c32k-all:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kat33/pulchra-c32k-all: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 kat33/pulchra-c32k-all:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kat33/pulchra-c32k-all:Q4_K_M

Use Docker

docker model run hf.co/kat33/pulchra-c32k-all:Q4_K_M

LM Studio
Jan

vLLM

How to use kat33/pulchra-c32k-all with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kat33/pulchra-c32k-all"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kat33/pulchra-c32k-all",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kat33/pulchra-c32k-all:Q4_K_M

SGLang

How to use kat33/pulchra-c32k-all 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 "kat33/pulchra-c32k-all" \
    --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": "kat33/pulchra-c32k-all",
		"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 "kat33/pulchra-c32k-all" \
        --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": "kat33/pulchra-c32k-all",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use kat33/pulchra-c32k-all with Ollama:
```
ollama run hf.co/kat33/pulchra-c32k-all:Q4_K_M
```

Unsloth Studio

How to use kat33/pulchra-c32k-all 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 kat33/pulchra-c32k-all 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 kat33/pulchra-c32k-all to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kat33/pulchra-c32k-all to start chatting

Atomic Chat new
Docker Model Runner
How to use kat33/pulchra-c32k-all with Docker Model Runner:
```
docker model run hf.co/kat33/pulchra-c32k-all:Q4_K_M
```

Lemonade

How to use kat33/pulchra-c32k-all with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kat33/pulchra-c32k-all:Q4_K_M

Run and chat with the model

lemonade run user.pulchra-c32k-all-Q4_K_M

List all available models

lemonade list

pulchra-c32k-all / status.txt

kat33

Upload status.txt with huggingface_hub

2f401d7 over 2 years ago

Raw

History Blame

848 Bytes

	Starting: Tue Oct 31 18:15:23 UTC 2023
	Total hours elapsed:

	OK ::: Reading configuration for mistral-7b-fun 0m0.014s
	OK ::: Installing binary requirements 0m0.002s
	OK ::: Installing py requirements 0m16.387s
	OK ::: Writing axolotl yaml config file: /workspace/qlorat1.yaml 0m0.053s
	OK ::: Cleaning up previous artifacts 0m0.002s
	OK ::: Logging into services 0m2.373s
	OK ::: Retrieve last checkpoint (if needed) 0m0.806s
	OK ::: Training model mistralai/Mistral-7B-v0.1 11m2.251s
	OK ::: Merging lora to base 1m42.326s
	OK ::: llama.cpp conversions 0m27.061s
	OK ::: Uploading merged model and lora to hf 9m43.267s
	OK ::: Quantizing model to Q4_K_M 2m33.223s
	OK ::: Uploading quantized mistral-7b-fun-b1-chunk32k-e4r64-Q4_K_M.gguf to hf 2m35.746s
	OK ::: Uploading /workspace/trlog.txt to hf 0m2.021s
	Exit: Tue Oct 31 18:43:48 UTC 2023