Instructions to use PracticeLLM/Custom-KoLLM-13B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v2")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PracticeLLM/Custom-KoLLM-13B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PracticeLLM/Custom-KoLLM-13B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v2

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v2 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 "PracticeLLM/Custom-KoLLM-13B-v2" \
    --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": "PracticeLLM/Custom-KoLLM-13B-v2",
		"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 "PracticeLLM/Custom-KoLLM-13B-v2" \
        --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": "PracticeLLM/Custom-KoLLM-13B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v2 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v2
```

kyujinpy commited on Nov 24, 2023

Commit

aa64d69

1 Parent(s): 515b9d0

Upload README.md

Browse files

Files changed (1) hide show

README.md +48 -0

README.md CHANGED Viewed

@@ -1,3 +1,51 @@
 ---
 license: cc-by-nc-sa-4.0
 ---

 ---
+language:
+- ko
+datasets:
+- kyujinpy/KOR-Orca-Platypus-kiwi
+library_name: transformers
+pipeline_tag: text-generation
 license: cc-by-nc-sa-4.0
 ---
+# **⭐My custom LLM 13B⭐**
+## Model Details
+**Model Developers**
+- Kyujin Han (kyujinpy)
+**Model Architecture**
+- My custom LLM 13B is an auto-regressive language model based on the LLaMA2 transformer architecture.
+**Base Model**
+- [beomi/llama-2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b)
+**Training Dataset**
+- [kyujinpy/KOR-Orca-Platypus-kiwi](https://huggingface.co/datasets/kyujinpy/KOR-Orca-Platypus-kiwi).
+---
+# Model comparisons
+> Ko-LLM leaderboard(11/25; [link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard))
+| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
+| --- | --- | --- | --- | --- | --- | --- |
+| ⭐My custom LLM 13B-v1⭐ | 50.19 | 45.99 | 56.93 | 41.78 | 41.66 | **64.58** |
+| **⭐My custom LLM 13B v2⭐** | NaN | NaN | NaN | NaN | NaN | NaN |
+# Implementation Code
+```python
+### KO-Platypus
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+repo = "PracticeLLM/Custom-KoLLM-13B-v2"
+OpenOrca = AutoModelForCausalLM.from_pretrained(
+        repo,
+        return_dict=True,
+        torch_dtype=torch.float16,
+        device_map='auto'
+)
+OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
+```
+---