Instructions to use llmixer/BigWeave-v31-96b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmixer/BigWeave-v31-96b with Transformers:

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

pipe = pipeline("text-generation", model="llmixer/BigWeave-v31-96b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmixer/BigWeave-v31-96b")
model = AutoModelForCausalLM.from_pretrained("llmixer/BigWeave-v31-96b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use llmixer/BigWeave-v31-96b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmixer/BigWeave-v31-96b"
# 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-v31-96b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmixer/BigWeave-v31-96b

SGLang

How to use llmixer/BigWeave-v31-96b 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-v31-96b" \
    --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-v31-96b",
		"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-v31-96b" \
        --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-v31-96b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmixer/BigWeave-v31-96b with Docker Model Runner:
```
docker model run hf.co/llmixer/BigWeave-v31-96b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BigWeave v31 96b

The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.

Prompting Format

llamav3

Merge process

This is a self-merge of meta-llama/Meta-Llama-3-70B-Instruct. Middle layers are duplicated and various matrices are scaled according to the template by jukofyork as shown here: https://github.com/arcee-ai/mergekit/issues/198#issuecomment-2079950009

Merge configuration:

const_tag: &MODEL meta-llama/Meta-Llama-3-70B-Instruct

const_tag: &RESIDUAL_SCALE_FACTOR 0.5
const_tag: &QK_ATTENUATION_FACTOR 0.7071067812
const_tag: &OUT_FACTOR 0.9

scale-filter-env: &scale_filter_env
  parameters:
    scale:
      - filter: o_proj
        value: *RESIDUAL_SCALE_FACTOR
      - filter: down_proj
        value: *RESIDUAL_SCALE_FACTOR
      - filter: q_proj
        value: *QK_ATTENUATION_FACTOR
      - filter: k_proj
        value: *QK_ATTENUATION_FACTOR
      - filter: v_proj
        value: *OUT_FACTOR
      - filter: up_proj
        value: *OUT_FACTOR
      - value: 1.0

slices:
  - sources:
    - model: *MODEL
      layer_range: [0, 25]

  - sources:
    - model: *MODEL
      layer_range: [25, 26]
      <<: *scale_filter_env

  - sources:
    - model: *MODEL
      layer_range: [25, 27]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [26, 28]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [27, 29]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [28, 30]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [29, 31]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [30, 32]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [31, 33]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [32, 34]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [33, 35]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [34, 36]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [35, 37]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [36, 38]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [37, 39]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [38, 40]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [39, 41]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [40, 42]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [41, 43]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [42, 44]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [43, 45]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [44, 46]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [45, 47]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [46, 48]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [47, 49]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [48, 50]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [49, 51]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [50, 52]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [51, 53]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [52, 54]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [53, 55]
      <<: *scale_filter_env

  - sources:
    - model: *MODEL
      layer_range: [54, 55]
      <<: *scale_filter_env
  - sources:
    - model: *MODEL
      layer_range: [55, 80]

merge_method: passthrough
dtype: float16

Downloads last month: 4

Safetensors

Model size

96B params

Tensor type

F16

Model tree for llmixer/BigWeave-v31-96b

Base model

meta-llama/Meta-Llama-3-70B

Finetuned

meta-llama/Meta-Llama-3-70B-Instruct

Finetuned

(48)

this model

Quantizations

2 models