Instructions to use grimjim/llama-3-experiment-v1-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/llama-3-experiment-v1-9B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/llama-3-experiment-v1-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/llama-3-experiment-v1-9B")
model = AutoModelForCausalLM.from_pretrained("grimjim/llama-3-experiment-v1-9B")
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 grimjim/llama-3-experiment-v1-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/llama-3-experiment-v1-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/llama-3-experiment-v1-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/llama-3-experiment-v1-9B

SGLang

How to use grimjim/llama-3-experiment-v1-9B 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 "grimjim/llama-3-experiment-v1-9B" \
    --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": "grimjim/llama-3-experiment-v1-9B",
		"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 "grimjim/llama-3-experiment-v1-9B" \
        --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": "grimjim/llama-3-experiment-v1-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/llama-3-experiment-v1-9B with Docker Model Runner:
```
docker model run hf.co/grimjim/llama-3-experiment-v1-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llama-3-experiment-v1-9B

This is an experimental merge, replicating additional layers to the model without post-merge healing. There is damage to the model, but it appears to be tolerable as is; the performance difference in benchmarks from the original 8B Instruct model does not appear to be significant. The resulting impact on narrative text completion may also be of interest.

Light testing performed with instruct prompting and the following sampler settings:

temp=1 and minP=0.02
temp=1 and smoothing factor=0.33

Full weights: grimjim/llama-3-experiment-v1-9B

GGUF quants: grimjim/llama-3-experiment-v1-9B-GGUF

This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using mergekit.

Built with Meta Llama 3.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

meta-llama/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: meta-llama/Meta-Llama-3-8B-Instruct
      layer_range: [0, 12]
  - sources:
    - model: meta-llama/Meta-Llama-3-8B-Instruct
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16