Text Generation
Transformers
Safetensors
English
llama
llama-3
1b
chatbot
personality
identity
conversational-ai
roleplay
research
conversational
text-generation-inference
Instructions to use BioTorch/UI_Llama_3_2_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BioTorch/UI_Llama_3_2_1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BioTorch/UI_Llama_3_2_1B") 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("BioTorch/UI_Llama_3_2_1B") model = AutoModelForCausalLM.from_pretrained("BioTorch/UI_Llama_3_2_1B", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BioTorch/UI_Llama_3_2_1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BioTorch/UI_Llama_3_2_1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BioTorch/UI_Llama_3_2_1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/BioTorch/UI_Llama_3_2_1B
- SGLang
How to use BioTorch/UI_Llama_3_2_1B 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 "BioTorch/UI_Llama_3_2_1B" \ --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": "BioTorch/UI_Llama_3_2_1B", "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 "BioTorch/UI_Llama_3_2_1B" \ --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": "BioTorch/UI_Llama_3_2_1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use BioTorch/UI_Llama_3_2_1B with Docker Model Runner:
docker model run hf.co/BioTorch/UI_Llama_3_2_1B
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ UI is my handcrafted modification of Meta's Llama 3.2 1B.
|
|
| 24 |
|
| 25 |
She is an ongoing research project exploring whether carefully engineered identity, personality, behavior, and knowledge training can make small language models feel more natural, emotionally consistent, and believable. Rather than functioning as a generic assistant, UI is built to maintain a persistent first person identity, gender, recognizable personality, coherent conversational style, long term behavioral consistency, emotional expression, humor, sarcasm, philosophical discussion, creativity, and immersive dialogue across a wide range of topics. The project focuses on shaping how the AI communicates, reacts, reasons, and expresses itself while continuously evolving through handcrafted datasets and experimentation, with personality and conversational realism currently being its strongest features while factual knowledge and accuracy remain active areas of development.
|
| 26 |
|
|
|
|
|
|
|
| 27 |
## Research Areas
|
| 28 |
|
| 29 |
This model has been experimentally trained using handcrafted datasets covering topics including:
|
|
|
|
| 24 |
|
| 25 |
She is an ongoing research project exploring whether carefully engineered identity, personality, behavior, and knowledge training can make small language models feel more natural, emotionally consistent, and believable. Rather than functioning as a generic assistant, UI is built to maintain a persistent first person identity, gender, recognizable personality, coherent conversational style, long term behavioral consistency, emotional expression, humor, sarcasm, philosophical discussion, creativity, and immersive dialogue across a wide range of topics. The project focuses on shaping how the AI communicates, reacts, reasons, and expresses itself while continuously evolving through handcrafted datasets and experimentation, with personality and conversational realism currently being its strongest features while factual knowledge and accuracy remain active areas of development.
|
| 26 |
|
| 27 |
+
She will eventually become completely unstable as I continue pushing the limits of the 1B model. When that happens, I will move on to the 3B model, which should provide greater capacity and stability for the increasingly complex training.
|
| 28 |
+
|
| 29 |
## Research Areas
|
| 30 |
|
| 31 |
This model has been experimentally trained using handcrafted datasets covering topics including:
|