Instructions to use tuantran1632001/Psyfighter2-Orca2-13B-ties with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tuantran1632001/Psyfighter2-Orca2-13B-ties with Transformers:

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

pipe = pipeline("text-generation", model="tuantran1632001/Psyfighter2-Orca2-13B-ties")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tuantran1632001/Psyfighter2-Orca2-13B-ties")
model = AutoModelForCausalLM.from_pretrained("tuantran1632001/Psyfighter2-Orca2-13B-ties")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tuantran1632001/Psyfighter2-Orca2-13B-ties with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tuantran1632001/Psyfighter2-Orca2-13B-ties"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tuantran1632001/Psyfighter2-Orca2-13B-ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tuantran1632001/Psyfighter2-Orca2-13B-ties

SGLang

How to use tuantran1632001/Psyfighter2-Orca2-13B-ties 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 "tuantran1632001/Psyfighter2-Orca2-13B-ties" \
    --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": "tuantran1632001/Psyfighter2-Orca2-13B-ties",
		"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 "tuantran1632001/Psyfighter2-Orca2-13B-ties" \
        --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": "tuantran1632001/Psyfighter2-Orca2-13B-ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tuantran1632001/Psyfighter2-Orca2-13B-ties with Docker Model Runner:
```
docker model run hf.co/tuantran1632001/Psyfighter2-Orca2-13B-ties
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Psyfighter2-Orca2-ties

Psyfighter2-Orca2-ties is a merge of the following models using mergekit:

This is my very first merge I have ever attempted. The motivation behind this merge is to try and create a 13B version of jebcarter/psyonic-cetacean-20B. I don't have a good GPU (GTX 1660 6GB), so although I can merge the model, I cannot actually run it. However, the Open LLM Leaderboard ranks this merge with 63.48 avg point, which is higher than both KoboldAI/LLaMA2-13B-Psyfighter2 and jebcarter/psyonic-cetacean-20B, so I must did something right. The next step is to quantize this merge into GGUF so I can actually run it with KoboldCpp.

🧩 Configuration

models:
  - model: KoboldAI/LLaMA2-13B-Psyfighter2
  - model: microsoft/Orca-2-13b
    parameters:
      density: 0.40
      weight: [0, 0.3, 0.7, 1]
merge_method: ties
base_model: KoboldAI/LLaMA2-13B-Psyfighter2
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.48
AI2 Reasoning Challenge (25-Shot)	62.46
HellaSwag (10-Shot)	81.74
MMLU (5-Shot)	60.31
TruthfulQA (0-shot)	55.40
Winogrande (5-shot)	77.27
GSM8k (5-shot)	43.67

Downloads last month: 110

Safetensors

Model size

13B params

Tensor type

F16

Model tree for tuantran1632001/Psyfighter2-Orca2-13B-ties

KoboldAI/LLaMA2-13B-Psyfighter2

microsoft/Orca-2-13b

Merge model

this model

Quantizations

4 models

Evaluation results

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

62.460
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

81.740
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

60.310
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

55.400
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

77.270
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

43.670