Instructions to use elinas/Llama-3-13B-Instruct-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elinas/Llama-3-13B-Instruct-ft with Transformers:

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

pipe = pipeline("text-generation", model="elinas/Llama-3-13B-Instruct-ft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("elinas/Llama-3-13B-Instruct-ft")
model = AutoModelForCausalLM.from_pretrained("elinas/Llama-3-13B-Instruct-ft")
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 elinas/Llama-3-13B-Instruct-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elinas/Llama-3-13B-Instruct-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "elinas/Llama-3-13B-Instruct-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/elinas/Llama-3-13B-Instruct-ft

SGLang

How to use elinas/Llama-3-13B-Instruct-ft 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 "elinas/Llama-3-13B-Instruct-ft" \
    --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": "elinas/Llama-3-13B-Instruct-ft",
		"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 "elinas/Llama-3-13B-Instruct-ft" \
        --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": "elinas/Llama-3-13B-Instruct-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use elinas/Llama-3-13B-Instruct-ft with Docker Model Runner:
```
docker model run hf.co/elinas/Llama-3-13B-Instruct-ft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-13B-Instruct-ft

This is a QLoRA finetune of a merge of pre-trained language models created using mergekit.

The model is based on my passthrough merge of Llama-3-13B-Instruct

This was primarily an experiment to see how a passthrough merge will respond to further finetuning, though this was done on a small dataset.

The goal was to make a "mid" sized model like Meta has released in the past and the merge method was inspired by mlabonne's Llama-3-120B.

The model was finetuned on 8192 context length and is likely reliable using RoPE up to 32k.

It still cannot do math reliably; neither can Llama-3-8B, and in my tests only Llama-3-70B passes basic arithmetic, but it is a better storywriter/RP than Llama-3-8B from some side by side testing I conducted.

Further finetuning this model or finetuning the base model on more samples is encouraged.

Datasets

Chat-Error/Pure-dove-sharegpt

A small dataset was used to see how it affects performance. Originally I planned to do a larger dataset (196k samples), but wanted to start with a smaller one first to see how much the model improved with some additional finetuning.

Next steps would be finetuning on a larger dataset if through further testing, performance improvements are noticed.

Finetuning details

This is a QLoRA model and all modules were targeted.

lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 3
- total_eval_batch_size: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 25
- num_epochs: 1

Optimizer paged_adamw_8bit and Deepspeed ZeRO 3 was used at a LR of 1e-5 using the cosine scheduler for 1 epoch on 3x3090s taking 4h 12m 13s total.

Sample packing and padding was disabled to reduce VRAM consumption significantly at the cost of speed.

W&B Run Summary

wandb: Run summary:
wandb:                eval/loss 1.00774
wandb:             eval/runtime 535.3847
wandb:  eval/samples_per_second 0.721
wandb:    eval/steps_per_second 0.241
wandb:               total_flos 4167452590080.0
wandb:              train/epoch 1.0
wandb:        train/global_step 1157
wandb:          train/grad_norm 4.50846
wandb:      train/learning_rate 0.0
wandb:               train/loss 1.4115
wandb:               train_loss 1.00352
wandb:            train_runtime 14921.1227
wandb: train_samples_per_second 0.233
wandb:   train_steps_per_second 0.078