Instructions to use ChuckMcSneed/WinterGoddess-1.4x-70b-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChuckMcSneed/WinterGoddess-1.4x-70b-32k with Transformers:

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

pipe = pipeline("text-generation", model="ChuckMcSneed/WinterGoddess-1.4x-70b-32k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ChuckMcSneed/WinterGoddess-1.4x-70b-32k")
model = AutoModelForMultimodalLM.from_pretrained("ChuckMcSneed/WinterGoddess-1.4x-70b-32k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ChuckMcSneed/WinterGoddess-1.4x-70b-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChuckMcSneed/WinterGoddess-1.4x-70b-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/WinterGoddess-1.4x-70b-32k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChuckMcSneed/WinterGoddess-1.4x-70b-32k

SGLang

How to use ChuckMcSneed/WinterGoddess-1.4x-70b-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/WinterGoddess-1.4x-70b-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/WinterGoddess-1.4x-70b-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/WinterGoddess-1.4x-70b-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/WinterGoddess-1.4x-70b-32k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChuckMcSneed/WinterGoddess-1.4x-70b-32k with Docker Model Runner:
```
docker model run hf.co/ChuckMcSneed/WinterGoddess-1.4x-70b-32k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a 32k version of Sao10K/WinterGoddess-1.4x-70B-L2, extended using method discussed here.

Quants

Thanks for GGUF, @Nexesenex!

GGUF

Benchmarks

NeoEvalPlusN_benchmark

My meme benchmark.

Test name	WinterGoddess	WinterGoddess-32k
B	2	2.5
C	1.5	2
D	3	0
S	2.75	1.5
P	5.5	2.25
Total	14.75	8.25

Open LLM Leaderboard Evaluation Results

Leaderboard on Huggingface

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
Sao10K/WinterGoddess-1.4x-70B-L2	73.23	72.78	90.11	71.12	65.76	85	54.59
ChuckMcSneed/WinterGoddess-1.4x-70b-32k	69.4	71.16	89.12	66.42	63.87	82.56	43.29
Difference	3.83	1.62	0.99	4.7	1.89	2.44	11.3

Here the losses seem far less brutal than on my bench. It seems that extending with LongLORA kills MMLU and GSM8K performance.

Detailed results can be found here

Metric	Value
Avg.	69.40
AI2 Reasoning Challenge (25-Shot)	71.16
HellaSwag (10-Shot)	89.12
MMLU (5-Shot)	66.42
TruthfulQA (0-shot)	63.87
Winogrande (5-shot)	82.56
GSM8k (5-shot)	43.29

Downloads last month: 82

Safetensors

Model size

69B params

Tensor type

F16

Model tree for ChuckMcSneed/WinterGoddess-1.4x-70b-32k

Quantizations

2 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

71.160
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

89.120
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

66.420
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

63.870
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.560
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

43.290