Instructions to use Corianas/microchar_moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Corianas/microchar_moe with Transformers:

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

pipe = pipeline("text-generation", model="Corianas/microchar_moe")

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

tokenizer = AutoTokenizer.from_pretrained("Corianas/microchar_moe")
model = AutoModelForCausalLM.from_pretrained("Corianas/microchar_moe", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Corianas/microchar_moe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Corianas/microchar_moe

SGLang

How to use Corianas/microchar_moe 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 "Corianas/microchar_moe" \
    --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": "Corianas/microchar_moe",
		"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 "Corianas/microchar_moe" \
        --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": "Corianas/microchar_moe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Corianas/microchar_moe with Docker Model Runner:
```
docker model run hf.co/Corianas/microchar_moe
```

microchar_moe / README.md

Corianas

Upload folder using huggingface_hub

cb6a088 verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.87 kB

---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Corianas/Microllama_Char_88k_step
base_model:
- Corianas/Microllama_Char_88k_step
- Corianas/Microllama_Char_88k_step
---
# microchar_moe
microchar_moe is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Corianas/Microllama_Char_88k_step](https://huggingface.co/Corianas/Microllama_Char_88k_step)
* [Corianas/Microllama_Char_88k_step](https://huggingface.co/Corianas/Microllama_Char_88k_step)

## 🧩 Configuration

```yaml
base_model: Corianas/Microllama_Char_88k_step 
gate_mode: random # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
## (optional)
# experts_per_token: 2
experts:
  - source_model: Corianas/Microllama_Char_88k_step
    positive_prompts:
      - ""
    ## (optional)
    # negative_prompts:
    #   - "This is a prompt expert_model_1 should not be used for"
  - source_model: Corianas/Microllama_Char_88k_step
    positive_prompts:
      - "" 
```

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Corianas/microchar_moe"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
```

	---
	license: apache-2.0
	tags:
	- moe
	- frankenmoe
	- merge
	- mergekit
	- lazymergekit
	- Corianas/Microllama_Char_88k_step
	base_model:
	- Corianas/Microllama_Char_88k_step
	- Corianas/Microllama_Char_88k_step
	---

	# microchar_moe

	microchar_moe is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
	* [Corianas/Microllama_Char_88k_step](https://huggingface.co/Corianas/Microllama_Char_88k_step)
	* [Corianas/Microllama_Char_88k_step](https://huggingface.co/Corianas/Microllama_Char_88k_step)

	## 🧩 Configuration

	```yaml
	base_model: Corianas/Microllama_Char_88k_step
	gate_mode: random # one of "hidden", "cheap_embed", or "random"
	dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
	## (optional)
	# experts_per_token: 2
	experts:
	- source_model: Corianas/Microllama_Char_88k_step
	positive_prompts:
	- ""
	## (optional)
	# negative_prompts:
	# - "This is a prompt expert_model_1 should not be used for"
	- source_model: Corianas/Microllama_Char_88k_step
	positive_prompts:
	- ""
	```

	## 💻 Usage

	```python
	!pip install -qU transformers bitsandbytes accelerate

	from transformers import AutoTokenizer
	import transformers
	import torch

	model = "Corianas/microchar_moe"

	tokenizer = AutoTokenizer.from_pretrained(model)
	pipeline = transformers.pipeline(
	"text-generation",
	model=model,
	model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
	)

	messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
	prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	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"])
	```