Instructions to use kirikir13/MOEmoe-3x7B-BF16-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kirikir13/MOEmoe-3x7B-BF16-v2 with Transformers:

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

pipe = pipeline("text-generation", model="kirikir13/MOEmoe-3x7B-BF16-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("kirikir13/MOEmoe-3x7B-BF16-v2")
model = AutoModelForCausalLM.from_pretrained("kirikir13/MOEmoe-3x7B-BF16-v2", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kirikir13/MOEmoe-3x7B-BF16-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kirikir13/MOEmoe-3x7B-BF16-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kirikir13/MOEmoe-3x7B-BF16-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kirikir13/MOEmoe-3x7B-BF16-v2

SGLang

How to use kirikir13/MOEmoe-3x7B-BF16-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 "kirikir13/MOEmoe-3x7B-BF16-v2" \
    --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": "kirikir13/MOEmoe-3x7B-BF16-v2",
		"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 "kirikir13/MOEmoe-3x7B-BF16-v2" \
        --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": "kirikir13/MOEmoe-3x7B-BF16-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kirikir13/MOEmoe-3x7B-BF16-v2 with Docker Model Runner:
```
docker model run hf.co/kirikir13/MOEmoe-3x7B-BF16-v2
```

kirikir13 commited on 3 days ago

Commit

0a7f22f

verified ·

1 Parent(s): 23df487

README: add The name section

Browse files

Files changed (1) hide show

README.md +8 -0

README.md CHANGED Viewed

@@ -20,6 +20,14 @@ Architecture: Built from 3 models: [M]  `MixtralForCausalLM` (`model_type: mixtr
 ---
 ## Why v2 exists
 The original upload [kirikir13/MOEmoe-3x7B-BF16](https://huggingface.co/kirikir13/MOEmoe-3x7B-BF16) (and its bucket copies) is **incomplete**: 19.3 GB of the ~37.0 GB model. It only has layers 0–15 and part of layer 16. Layers 16–31, all 32 router (`gate`) weights, `model.norm` and `lm_head` are missing (upload/hard-drive failure). The original is left untouched. This repo is a full rebuild from the same source models with mergekit-moe.

 ---
+## The name
+**MOEmoe = "Mistral of Experts".** Three Mistral-family 7B models whose initials spell **M-O-E**:
+- **M** = Mistral-7B-Instruct-v0.2, the main talker ("Minstrel" in the original note was a spelling slip for Mistral)
+- **O** = OpenChat-3.5, logic and reasoning
+- **E** = Eurus-7b-kto, math
+They share the same tokenizer and tensor shapes, so they frankenmerge cleanly into one Mixtral-style MoE.
 ## Why v2 exists
 The original upload [kirikir13/MOEmoe-3x7B-BF16](https://huggingface.co/kirikir13/MOEmoe-3x7B-BF16) (and its bucket copies) is **incomplete**: 19.3 GB of the ~37.0 GB model. It only has layers 0–15 and part of layer 16. Layers 16–31, all 32 router (`gate`) weights, `model.norm` and `lm_head` are missing (upload/hard-drive failure). The original is left untouched. This repo is a full rebuild from the same source models with mergekit-moe.