Instructions to use ChuckMcSneed/WinterGoliath-123b-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChuckMcSneed/WinterGoliath-123b-32k with Transformers:

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

pipe = pipeline("text-generation", model="ChuckMcSneed/WinterGoliath-123b-32k")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChuckMcSneed/WinterGoliath-123b-32k")
model = AutoModelForCausalLM.from_pretrained("ChuckMcSneed/WinterGoliath-123b-32k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ChuckMcSneed/WinterGoliath-123b-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChuckMcSneed/WinterGoliath-123b-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChuckMcSneed/WinterGoliath-123b-32k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChuckMcSneed/WinterGoliath-123b-32k

SGLang

How to use ChuckMcSneed/WinterGoliath-123b-32k 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 "ChuckMcSneed/WinterGoliath-123b-32k" \
    --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": "ChuckMcSneed/WinterGoliath-123b-32k",
		"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 "ChuckMcSneed/WinterGoliath-123b-32k" \
        --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": "ChuckMcSneed/WinterGoliath-123b-32k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChuckMcSneed/WinterGoliath-123b-32k with Docker Model Runner:
```
docker model run hf.co/ChuckMcSneed/WinterGoliath-123b-32k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a merge of Xwin and WinterGoddess, both extended to 32k using the method discussed here.

Smarter than Goliath-32k, but has some quirks.

A bit damaged compared to original WinterGoliath.

Prompt format

Vicuna or Alpaca.

Benchmarks

NeoEvalPlusN_benchmark

My meme benchmark.

Test name	WinterGoliath-32k	WinterGoliath
B	3	3
C	2	2
D	1	2
S	3.75	5.5
P	3.75	6
Total	13.5	18.5

Downloads last month: 37

Safetensors

Model size

124B params

Tensor type

F16

Model tree for ChuckMcSneed/WinterGoliath-123b-32k

Quantizations

2 models