Instructions to use llmixer/BigWeave-v6-90b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmixer/BigWeave-v6-90b with Transformers:

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

pipe = pipeline("text-generation", model="llmixer/BigWeave-v6-90b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmixer/BigWeave-v6-90b")
model = AutoModelForCausalLM.from_pretrained("llmixer/BigWeave-v6-90b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use llmixer/BigWeave-v6-90b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmixer/BigWeave-v6-90b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmixer/BigWeave-v6-90b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmixer/BigWeave-v6-90b

SGLang

How to use llmixer/BigWeave-v6-90b 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 "llmixer/BigWeave-v6-90b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmixer/BigWeave-v6-90b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "llmixer/BigWeave-v6-90b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmixer/BigWeave-v6-90b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmixer/BigWeave-v6-90b with Docker Model Runner:
```
docker model run hf.co/llmixer/BigWeave-v6-90b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:The pipeline tag "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

BigWeave v6 90B

A Goliath-120b style frankenmerge of Xwin-LM-70b-v0.1 and Euryale-1.3-70b. The goal is to find other merge combinations that work well.

The version number is for me to keep track of the merges, only results that seem to work reasonably well are kept/published.

Prompting Format

Vicuna and Alpaca.

Merge process

The models used in the merge are Xwin-LM-70b-v0.1 and Euryale-1.3-70b.

The layer mix:

- range 0, 12
  Xwin
- range 9, 14
  Euryale
- range 12, 62
  Xwin
- range 54, 71
  Euryale
- range 62, 80
  Xwin

Acknowledgements

@Xwin-LM For creating Xwin

@Sao10K For creating Euryale

@alpindale For creating the original Goliath

@chargoddard For developing mergekit.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.47
AI2 Reasoning Challenge (25-Shot)	65.36
HellaSwag (10-Shot)	87.21
MMLU (5-Shot)	68.04
TruthfulQA (0-shot)	57.96
Winogrande (5-shot)	81.69
GSM8k (5-shot)	44.58

Downloads last month: 69

Safetensors

Model size

88B params

Tensor type

F16

Model tree for llmixer/BigWeave-v6-90b

Quantizations

2 models

Collection including llmixer/BigWeave-v6-90b

BigWeave Viable

Collection

All viable models from the BigWeave series, excluding quantized versions • 7 items • Updated Feb 15, 2024

Evaluation results

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

65.360
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.210
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

68.040
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.960
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

81.690
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

44.580