Instructions to use kyujinpy/PlatYi-34B-Llama-Q-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyujinpy/PlatYi-34B-Llama-Q-v2 with Transformers:

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

pipe = pipeline("text-generation", model="kyujinpy/PlatYi-34B-Llama-Q-v2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyujinpy/PlatYi-34B-Llama-Q-v2")
model = AutoModelForCausalLM.from_pretrained("kyujinpy/PlatYi-34B-Llama-Q-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kyujinpy/PlatYi-34B-Llama-Q-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyujinpy/PlatYi-34B-Llama-Q-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/PlatYi-34B-Llama-Q-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kyujinpy/PlatYi-34B-Llama-Q-v2

SGLang

How to use kyujinpy/PlatYi-34B-Llama-Q-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 "kyujinpy/PlatYi-34B-Llama-Q-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": "kyujinpy/PlatYi-34B-Llama-Q-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 "kyujinpy/PlatYi-34B-Llama-Q-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": "kyujinpy/PlatYi-34B-Llama-Q-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kyujinpy/PlatYi-34B-Llama-Q-v2 with Docker Model Runner:
```
docker model run hf.co/kyujinpy/PlatYi-34B-Llama-Q-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PlatYi-34B-Llama-Q-v2

Model Details

Model Developers Kyujin Han (kyujinpy)

Input Models input text only.

Output Models generate text only.

Model Architecture
PlatYi-34B-Llama-Q-v2 is an auto-regressive language model based on the Yi-34B transformer architecture.

Blog Link
Blog: [Coming soon...]
Github: [Coming soon...]

Base Model
chargoddard/Yi-34B-Llama

Training Dataset
garage-bAInd/Open-Platypus.

Fix some bugs

Before model, there is some mistakes.
I modified the templates and warmup_steps.

Notice

While training, I used Q-LoRA. The lora_r values is 64.

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
PlatYi-34B-Llama-Q-v2	67.88	61.09	85.09	76.59	52.65	82.79	49.05
PlatYi-34B-Llama-Q	71.13	65.70	85.22	78.78	53.64	83.03	60.42
PlatYi-34B-Llama	68.37	67.83	85.35	78.26	53.46	82.87	42.46
Yi-34B-Llama	70.95	64.59	85.63	76.31	55.60	82.79	60.80
Yi-34B	69.42	64.59	85.69	76.35	56.23	83.03	50.64

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/PlatYi-34B-Llama-Q-v2"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.88
AI2 Reasoning Challenge (25-Shot)	61.09
HellaSwag (10-Shot)	85.09
MMLU (5-Shot)	76.59
TruthfulQA (0-shot)	52.65
Winogrande (5-shot)	82.79
GSM8k (5-shot)	49.05

Downloads last month: 56

Safetensors

Model size

34B params

Tensor type

F16

Model tree for kyujinpy/PlatYi-34B-Llama-Q-v2

Quantizations

3 models

Dataset used to train kyujinpy/PlatYi-34B-Llama-Q-v2

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

61.090
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.090
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

76.590
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

52.650
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.790
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

49.050