Instructions to use RDson/Llama-3-5B-Experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RDson/Llama-3-5B-Experimental with Transformers:

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

pipe = pipeline("text-generation", model="RDson/Llama-3-5B-Experimental")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RDson/Llama-3-5B-Experimental")
model = AutoModelForCausalLM.from_pretrained("RDson/Llama-3-5B-Experimental")
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 Settings

vLLM

How to use RDson/Llama-3-5B-Experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RDson/Llama-3-5B-Experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RDson/Llama-3-5B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RDson/Llama-3-5B-Experimental

SGLang

How to use RDson/Llama-3-5B-Experimental 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 "RDson/Llama-3-5B-Experimental" \
    --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": "RDson/Llama-3-5B-Experimental",
		"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 "RDson/Llama-3-5B-Experimental" \
        --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": "RDson/Llama-3-5B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RDson/Llama-3-5B-Experimental with Docker Model Runner:
```
docker model run hf.co/RDson/Llama-3-5B-Experimental
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is just an experiment similar to that done on chargoddard/llama3-42b-v0. The post-pruning was fine-tuned or "healed" with QLoRA using the code DPO dataset AlekseyKorshuk/evol-codealpaca-v1-dpo. Due to limitations, this was only trained on 3150/4935 (~64%) steps of the data. I had to restart the training about halfway through, so the logs are split in two. I am still unsure if the tokenizer is correct.

Loss: ~1.2

mergekit.yaml

slices:
  - sources:
      - model: ./Meta-Llama-3-8B-Instruct/
        layer_range: [0,15]
  - sources:
      - model: ./Meta-Llama-3-8B-Instruct/
        layer_range: [29,32]
            
merge_method: passthrough
dtype: bfloat16

ORPOConfig

    learning_rate=5e-5,
    lr_scheduler_type="cosine",
    max_length=1024,
    max_prompt_length=512,
    overwrite_output_dir=False,
    beta=0.1,
    per_device_train_batch_size=2,
    per_device_eval_batch_size=2,
    gradient_accumulation_steps=4,
    optim="paged_adamw_8bit",
    num_train_epochs=1,
    evaluation_strategy="steps",
    eval_steps=0.02,
    logging_steps=1,
    warmup_steps=50,
    report_to="wandb",
    output_dir=out_dir_folder,
    fp16=True,
    save_steps=50

Downloads last month: 1

Safetensors

Model size

5B params

Tensor type

F16

Model tree for RDson/Llama-3-5B-Experimental

Quantizations

1 model