Instructions to use kuotient/Llama-3-11B-Instruct-attenuated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kuotient/Llama-3-11B-Instruct-attenuated with Transformers:

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

pipe = pipeline("text-generation", model="kuotient/Llama-3-11B-Instruct-attenuated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kuotient/Llama-3-11B-Instruct-attenuated")
model = AutoModelForCausalLM.from_pretrained("kuotient/Llama-3-11B-Instruct-attenuated")
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 kuotient/Llama-3-11B-Instruct-attenuated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuotient/Llama-3-11B-Instruct-attenuated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/Llama-3-11B-Instruct-attenuated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kuotient/Llama-3-11B-Instruct-attenuated

SGLang

How to use kuotient/Llama-3-11B-Instruct-attenuated 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 "kuotient/Llama-3-11B-Instruct-attenuated" \
    --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": "kuotient/Llama-3-11B-Instruct-attenuated",
		"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 "kuotient/Llama-3-11B-Instruct-attenuated" \
        --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": "kuotient/Llama-3-11B-Instruct-attenuated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kuotient/Llama-3-11B-Instruct-attenuated with Docker Model Runner:
```
docker model run hf.co/kuotient/Llama-3-11B-Instruct-attenuated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-11.5B-Instruct-attenuated

The core idea came from @jukofyork, see this issue;

As I understand, The concept of the idea is to make model think twice but leap same distances like original. but why 0.7071067812?

The scale factor to use, eg: solve x^2 = 1/2 --> x = 1/sqrt(2) ≈ 0.7071067812

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

kuotient/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

###############################
# llama-3-attenuated.yaml #
###############################

# Use: mergekit-yaml --clone-tensors ./llama-3-attenuated.yaml ./llama-3-attenuated
# See: https://github.com/arcee-ai/mergekit/issues/198 for discussion/reasoning behind this idea.

# ---

# The scale factor to use, eg: solve x^2 = 1/2 --> x = 1/sqrt(2) ≈ 0.7071067812
const_tag: &scale_factor 0.7071067812 # 1/sqrt(2)

# The filter parameters of a scaled block. 
attenuate-env: &attenuated_env
  parameters:
    scale:
      - filter: q_proj
        value: *scale_factor
      - filter: k_proj
        value: *scale_factor
      - value: 1.0

# ---

slices:

  ###########################
  # Block 1: miqu-1 [0, 16] #
  ###########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [0, 8] # The first 8 layers of Block 1 are not duplicated
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [8, 16] # The last 8 layers of Block 1 are are duplicated twice
      <<: *attenuated_env

  ###########################
  # Block 2: miqu-1 [8, 24] #
  ###########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [8, 24] # All the layers of Block 2 are are duplicated twice
      <<: *attenuated_env

  ##########################
  # Block 3: miqu-1 [16, 32] #
  ##########################
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [16, 24] # The first 8 layers of Block 3 are are duplicated twice
      <<: *attenuated_env
  - sources:
    - model: kuotient/Meta-Llama-3-8B-Instruct
      layer_range: [24, 32] # The last 8 layers of Block 3 are not duplicated

merge_method: passthrough
dtype: bfloat16

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for kuotient/Llama-3-11B-Instruct-attenuated

Base model

kuotient/Meta-Llama-3-8B-Instruct

Finetuned

(2)

this model

Finetunes

1 model

Quantizations

1 model