Instructions to use ping98k/open_llama_3b_v2_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ping98k/open_llama_3b_v2_4bit with Transformers:

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

pipe = pipeline("text-generation", model="ping98k/open_llama_3b_v2_4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ping98k/open_llama_3b_v2_4bit")
model = AutoModelForCausalLM.from_pretrained("ping98k/open_llama_3b_v2_4bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ping98k/open_llama_3b_v2_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ping98k/open_llama_3b_v2_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ping98k/open_llama_3b_v2_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ping98k/open_llama_3b_v2_4bit

SGLang

How to use ping98k/open_llama_3b_v2_4bit 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 "ping98k/open_llama_3b_v2_4bit" \
    --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": "ping98k/open_llama_3b_v2_4bit",
		"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 "ping98k/open_llama_3b_v2_4bit" \
        --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": "ping98k/open_llama_3b_v2_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ping98k/open_llama_3b_v2_4bit with Docker Model Runner:
```
docker model run hf.co/ping98k/open_llama_3b_v2_4bit
```

open_llama_3b_v2_4bit / README.md

ping98k

Add README

1f8ebfa verified about 2 months ago

preview code

raw

history blame contribute delete

1.26 kB

metadata

library_name: transformers
base_model: openlm-research/open_llama_3b_v2
tags:
  - 4bit
  - bnb
  - nf4
  - qlora
  - llama
quantized_by: ping98k

Open LLaMA 3B v2 — 4-bit NF4

4-bit quantized version of openlm-research/open_llama_3b_v2 using bitsandbytes NF4, ready for QLoRA fine-tuning.

Quantization Details

Parameter	Value
Quant method	bitsandbytes NF4
Double quant	Yes
Compute dtype	bfloat16
Model size	~1.93 GB

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ping98k/open_llama_3b_v2_4bit", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("ping98k/open_llama_3b_v2_4bit")

QLoRA Fine-tuning

from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training

model.gradient_checkpointing_enable()
model = prepare_model_for_kbit_training(model)

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
)
model = get_peft_model(model, lora_config)