Instructions to use HaileyStorm/llama3-5.4b-instruct-unhealed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HaileyStorm/llama3-5.4b-instruct-unhealed with Transformers:

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

pipe = pipeline("text-generation", model="HaileyStorm/llama3-5.4b-instruct-unhealed")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HaileyStorm/llama3-5.4b-instruct-unhealed")
model = AutoModelForCausalLM.from_pretrained("HaileyStorm/llama3-5.4b-instruct-unhealed")
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 HaileyStorm/llama3-5.4b-instruct-unhealed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HaileyStorm/llama3-5.4b-instruct-unhealed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HaileyStorm/llama3-5.4b-instruct-unhealed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HaileyStorm/llama3-5.4b-instruct-unhealed

SGLang

How to use HaileyStorm/llama3-5.4b-instruct-unhealed 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 "HaileyStorm/llama3-5.4b-instruct-unhealed" \
    --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": "HaileyStorm/llama3-5.4b-instruct-unhealed",
		"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 "HaileyStorm/llama3-5.4b-instruct-unhealed" \
        --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": "HaileyStorm/llama3-5.4b-instruct-unhealed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HaileyStorm/llama3-5.4b-instruct-unhealed with Docker Model Runner:
```
docker model run hf.co/HaileyStorm/llama3-5.4b-instruct-unhealed
```

merged

This is a "merge" of pre-trained language models created using mergekit. It is a prune of Meta-Llama-3-8B-Instruct down to 20 layers, or about 5.4B parameter. Mostly, this is a test of pruning & healing an instruct-tuned model. THIS MODEL HAS NOT BEEN HEALED. It is presently unusable. The healed version will be in a different repository. This size should allow bf16 inference on 24GB VRAM, Q8 or Q6 inference on 6GB VRAM, Q5 inference on 4GB VRAM, and fine-tuning ... well, with less VRAM than an 8B model.

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:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 16]
    model: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
  - layer_range: [20, 21]
    model: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
  - layer_range: [29, 32]
    model: meta-llama/Meta-Llama-3-8B-Instruct

Downloads last month: 2

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for HaileyStorm/llama3-5.4b-instruct-unhealed

Base model

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

Finetuned

(1117)

this model