Instructions to use SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora with Transformers:

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

pipe = pipeline("text-generation", model="SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora")
model = AutoModelForMultimodalLM.from_pretrained("SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora")
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 SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora

SGLang

How to use SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora 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 "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora" \
    --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": "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora",
		"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 "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora" \
        --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": "SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora with Docker Model Runner:
```
docker model run hf.co/SebastianSchramm/Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora
```

Sheared-LLaMA-1.3B-sft-lora-merged-dpo-lora / all_results.json

SebastianSchramm

Model save

06c1b50 over 2 years ago

raw

history blame contribute delete

744 Bytes

	{
	"epoch": 3.0,
	"eval_logits/chosen": 1.923162579536438,
	"eval_logits/rejected": 1.5247185230255127,
	"eval_logps/chosen": -390.9497985839844,
	"eval_logps/rejected": -310.8146057128906,
	"eval_loss": 0.5420426726341248,
	"eval_rewards/accuracies": 0.7235000133514404,
	"eval_rewards/chosen": 0.16164450347423553,
	"eval_rewards/margins": 0.6670746803283691,
	"eval_rewards/rejected": -0.5054302215576172,
	"eval_runtime": 803.2883,
	"eval_samples": 2000,
	"eval_samples_per_second": 2.49,
	"eval_steps_per_second": 0.622,
	"train_loss": 0.5633580120213061,
	"train_runtime": 136089.4761,
	"train_samples": 61966,
	"train_samples_per_second": 1.366,
	"train_steps_per_second": 0.021
	}