Instructions to use Yuma42/KangalKhan-RawRuby-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yuma42/KangalKhan-RawRuby-7B with Transformers:

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

pipe = pipeline("text-generation", model="Yuma42/KangalKhan-RawRuby-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yuma42/KangalKhan-RawRuby-7B")
model = AutoModelForCausalLM.from_pretrained("Yuma42/KangalKhan-RawRuby-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Yuma42/KangalKhan-RawRuby-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yuma42/KangalKhan-RawRuby-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuma42/KangalKhan-RawRuby-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yuma42/KangalKhan-RawRuby-7B

SGLang

How to use Yuma42/KangalKhan-RawRuby-7B 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 "Yuma42/KangalKhan-RawRuby-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuma42/KangalKhan-RawRuby-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Yuma42/KangalKhan-RawRuby-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yuma42/KangalKhan-RawRuby-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yuma42/KangalKhan-RawRuby-7B with Docker Model Runner:
```
docker model run hf.co/Yuma42/KangalKhan-RawRuby-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

KangalKhan-RawRuby-7B

I suggest using ChatML (Use whatever system prompt you like, this is just an example!):

<|im_start|>system
You are a friendly assistant.<|im_end|>
<|im_start|>user
Hello, what are you?<|im_end|>
<|im_start|>assistant
I am an AI language model designed to assist users with information and answer their questions. How can I help you today?<|im_end|>

Q4_K_S GGUF:
https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B-GGUF

More GGUF variants by mradermacher:
WARNING: I have observed that these versions output typos in rare cases. If you have the same problem, use my Q4_K_S GGUF above. https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-GGUF weighted/imatrix GGUF by mradermacher:
https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-i1-GGUF

KangalKhan-RawRuby-7B is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: Yuma42/KangalKhan-Ruby-7B-Fixed
        layer_range: [0, 32]
      - model: Yuma42/KangalKhan-RawEmerald-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Yuma42/KangalKhan-Ruby-7B-Fixed
parameters:
  t:
    - filter: self_attn
      value: [0.1, 0.55, 0.35, 0.75, 0.97]
    - filter: mlp
      value: [0.9, 0.45, 0.65, 0.25, 0.03]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Yuma42/KangalKhan-RawRuby-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.95
AI2 Reasoning Challenge (25-Shot)	66.89
HellaSwag (10-Shot)	85.53
MMLU (5-Shot)	63.46
TruthfulQA (0-shot)	57.09
Winogrande (5-shot)	78.69
GSM8k (5-shot)	62.02

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.38
IFEval (0-Shot)	54.77
BBH (3-Shot)	26.39
MATH Lvl 5 (4-Shot)	5.97
GPQA (0-shot)	5.03
MuSR (0-shot)	7.64
MMLU-PRO (5-shot)	22.48

Downloads last month: 88

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Yuma42/KangalKhan-RawRuby-7B

Yuma42/KangalKhan-RawEmerald-7B

Yuma42/KangalKhan-Ruby-7B-Fixed

Merge model

this model

Quantizations

2 models

Evaluation results

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

66.890
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.530
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.460
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.090
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

78.690
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

62.020
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

54.770
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

26.390
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

5.970
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

5.030
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

7.640
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

22.480