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

Libraries

How to use jbomdev/AlterEgo with Transformers:

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

pipe = pipeline("text-generation", model="jbomdev/AlterEgo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jbomdev/AlterEgo")
model = AutoModelForCausalLM.from_pretrained("jbomdev/AlterEgo", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jbomdev/AlterEgo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jbomdev/AlterEgo

SGLang

How to use jbomdev/AlterEgo 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 "jbomdev/AlterEgo" \
    --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": "jbomdev/AlterEgo",
		"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 "jbomdev/AlterEgo" \
        --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": "jbomdev/AlterEgo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

jbomdev commited on Jun 22

Commit

f66ef7a

verified ·

1 Parent(s): 5bcb323

add GGUF mentions

Browse files

Files changed (1) hide show

README.md +10 -1

README.md CHANGED Viewed

@@ -58,6 +58,7 @@ model-index:
 [![Platform](https://img.shields.io/badge/GitHub-LLME%20(platform)-181717?logo=github)](https://github.com/J-bom/LLME)
 [![Architecture](https://img.shields.io/badge/arch-Llama--style-blue)]()
 [![Params](https://img.shields.io/badge/params-373M-green)]()
 </div>
@@ -178,6 +179,7 @@ out = model.generate(
 print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
 ```
 ### Recommended generation settings
 These are the defaults AlterEgo was tuned and served with in LLME:
@@ -206,12 +208,19 @@ AlterEgo uses **ChatML**:
 ### Run it locally (GGUF)
-Because it's standard Llama format, you can convert to GGUF for Ollama / LM Studio / llama.cpp:
 ```bash
 python llama.cpp/convert_hf_to_gguf.py ./AlterEgo --outfile alterego-f16.gguf --outtype f16
 ```
 ## Limitations
 AlterEgo is a 373M-parameter model trained on a modest token budget, and it behaves like one:

 [![Platform](https://img.shields.io/badge/GitHub-LLME%20(platform)-181717?logo=github)](https://github.com/J-bom/LLME)
 [![Architecture](https://img.shields.io/badge/arch-Llama--style-blue)]()
 [![Params](https://img.shields.io/badge/params-373M-green)]()
+[![Format](https://img.shields.io/badge/format-GGUF-orange)]()
 </div>
 print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
 ```
 ### Recommended generation settings
 These are the defaults AlterEgo was tuned and served with in LLME:
 ### Run it locally (GGUF)
+Feel free to use my pre-made GGUF's and quants by visiting [The GGUF's and quants page](https://huggingface.co/jbomdev/AlterEgo-GGUF).
+Or running the model with [ollama](https://ollama.com/jbomdev/alterego).
+Also, Because it's standard Llama format, you can convert to GGUF for Ollama / LM Studio / llama.cpp yourself:
 ```bash
 python llama.cpp/convert_hf_to_gguf.py ./AlterEgo --outfile alterego-f16.gguf --outtype f16
 ```
 ## Limitations
 AlterEgo is a 373M-parameter model trained on a modest token budget, and it behaves like one: