Instructions to use philschmid/shepherd-2-hf-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philschmid/shepherd-2-hf-int4 with Transformers:

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

pipe = pipeline("text-generation", model="philschmid/shepherd-2-hf-int4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("philschmid/shepherd-2-hf-int4")
model = AutoModelForCausalLM.from_pretrained("philschmid/shepherd-2-hf-int4")

Inference
Local Apps Settings

vLLM

How to use philschmid/shepherd-2-hf-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philschmid/shepherd-2-hf-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philschmid/shepherd-2-hf-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/philschmid/shepherd-2-hf-int4

SGLang

How to use philschmid/shepherd-2-hf-int4 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 "philschmid/shepherd-2-hf-int4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philschmid/shepherd-2-hf-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "philschmid/shepherd-2-hf-int4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philschmid/shepherd-2-hf-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use philschmid/shepherd-2-hf-int4 with Docker Model Runner:
```
docker model run hf.co/philschmid/shepherd-2-hf-int4
```

Fine-tuned Llama 2 on sheperd

from datasets import load_dataset 
from random import randrange
import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer


output_dir = "philschmid/shepherd-2-hf-int4"

# load base LLM model and tokenizer
model = AutoPeftModelForCausalLM.from_pretrained(
    output_dir,
    low_cpu_mem_usage=True,
    torch_dtype=torch.float16,
    load_in_4bit=True,
) 
tokenizer = AutoTokenizer.from_pretrained(output_dir)


# Load dataset from the hub and get a sample
dataset = load_dataset("philschmid/meta-shepherd-human-data", split="train")
sample = dataset[randrange(len(dataset))]

prompt = f"""### Question: {sample['question']}

### Answer:
{sample['answer']}

### Feedback:
"""

input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
# with torch.inference_mode():
outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.9)

print(prompt[:-14])
print("---"*35)
print(f"### Generated Feedback:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
print(f"### Ground truth Feedback:\n{sample['feedback']}")

Training procedure

The following bitsandbytes quantization config was used during training:

load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: True
bnb_4bit_compute_dtype: bfloat16

Framework versions

PEFT 0.4.0

Downloads last month: 17