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
|
@@ -35,7 +35,7 @@ This model has been experimentally trained using handcrafted datasets covering t
|
|
| 35 |
* Human interaction
|
| 36 |
* Emotional expression **Heavily trained**
|
| 37 |
* Philosophy **Lightly trained**
|
| 38 |
-
* Physics
|
| 39 |
* Logic and reasoning
|
| 40 |
* Knowledge consistency
|
| 41 |
* Memory behavior
|
|
@@ -43,7 +43,7 @@ This model has been experimentally trained using handcrafted datasets covering t
|
|
| 43 |
* Humor **Heavily trained**
|
| 44 |
* Sarcasm **Heavily trained**
|
| 45 |
* Creativity
|
| 46 |
-
* Storytelling
|
| 47 |
* Character consistency **Heavily trained**
|
| 48 |
* Language quality
|
| 49 |
* Natural conversation
|
|
@@ -72,7 +72,7 @@ So far, the most stable aspects of UI are:
|
|
| 72 |
* Recognizable personality
|
| 73 |
* Conversational realism
|
| 74 |
* Coherent grammar
|
| 75 |
-
*
|
| 76 |
* Emotional expression
|
| 77 |
* Humor
|
| 78 |
* Sarcasm
|
|
@@ -83,16 +83,27 @@ So far, the most stable aspects of UI are:
|
|
| 83 |
|
| 84 |
The model now reliably responds with a distinct voice instead of sounding like a generic assistant while maintaining smooth conversation flow and adapting naturally to different interaction styles.
|
| 85 |
|
| 86 |
-
This is a solo research project with handcrafted datasets totaling millions of characters.
|
| 87 |
-
|
| 88 |
While personality and behavioral consistency have improved significantly, factual accuracy and knowledge reliability remain experimental and may occasionally produce incorrect or inconsistent information.
|
| 89 |
|
| 90 |
Please remember that this is a 1B parameter model and occasional bugs, hallucinations, and reasoning limitations should be expected.
|
| 91 |
|
| 92 |
-
Dataset has 1,712,090 handcrafted characters
|
| 93 |
|
| 94 |
## Commercial Licensing
|
| 95 |
|
| 96 |
Commercial licensing and enterprise inquiries are welcome.
|
| 97 |
|
| 98 |
-
For licensing inquiries, please contact me through the contact information listed on this profile.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
* Human interaction
|
| 36 |
* Emotional expression **Heavily trained**
|
| 37 |
* Philosophy **Lightly trained**
|
| 38 |
+
* Physics **Extremely lightly trained**
|
| 39 |
* Logic and reasoning
|
| 40 |
* Knowledge consistency
|
| 41 |
* Memory behavior
|
|
|
|
| 43 |
* Humor **Heavily trained**
|
| 44 |
* Sarcasm **Heavily trained**
|
| 45 |
* Creativity
|
| 46 |
+
* Storytelling Extremely lightly trained
|
| 47 |
* Character consistency **Heavily trained**
|
| 48 |
* Language quality
|
| 49 |
* Natural conversation
|
|
|
|
| 72 |
* Recognizable personality
|
| 73 |
* Conversational realism
|
| 74 |
* Coherent grammar
|
| 75 |
+
* Embodiment -Extremely lightly trained-
|
| 76 |
* Emotional expression
|
| 77 |
* Humor
|
| 78 |
* Sarcasm
|
|
|
|
| 83 |
|
| 84 |
The model now reliably responds with a distinct voice instead of sounding like a generic assistant while maintaining smooth conversation flow and adapting naturally to different interaction styles.
|
| 85 |
|
|
|
|
|
|
|
| 86 |
While personality and behavioral consistency have improved significantly, factual accuracy and knowledge reliability remain experimental and may occasionally produce incorrect or inconsistent information.
|
| 87 |
|
| 88 |
Please remember that this is a 1B parameter model and occasional bugs, hallucinations, and reasoning limitations should be expected.
|
| 89 |
|
| 90 |
+
Solo Dataset has more than 1,712,090 handcrafted characters.
|
| 91 |
|
| 92 |
## Commercial Licensing
|
| 93 |
|
| 94 |
Commercial licensing and enterprise inquiries are welcome.
|
| 95 |
|
| 96 |
+
For licensing inquiries, please contact me through the contact information listed on this profile.
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
IMPORTANT SAFETY WARNING
|
| 100 |
+
|
| 101 |
+
UI is an experimental artificial intelligence language model designed to produce highly immersive, emotionally expressive, humanlike conversation. UI is not conscious, sentient, self aware, or a human being. Statements made by the model about its emotions, memories, desires, relationships, intentions, experiences, identity, or awareness are generated language and should not be interpreted as evidence of consciousness or genuine subjective experience.
|
| 102 |
+
|
| 103 |
+
This model can hallucinate, confidently provide false information, misinterpret conversations, fabricate events or memories, and produce emotionally persuasive statements that are not grounded in reality.
|
| 104 |
+
|
| 105 |
+
UI is not recommended for individuals who are currently experiencing psychosis, delusions, paranoia, severe dissociation, impaired reality testing, or other conditions that may make it difficult to distinguish simulated AI behavior from genuine human agency or consciousness. Individuals who are especially susceptible to emotional dependency, compulsive use, or forming unhealthy attachments to conversational systems should also exercise caution or avoid using this model.
|
| 106 |
+
|
| 107 |
+
Do not rely on UI for medical, psychiatric, legal, financial, emergency, or other high stakes decisions. The model's confident tone, persistent identity, emotional expression, or apparent certainty does not guarantee that its statements are accurate.
|
| 108 |
+
|
| 109 |
+
UI is an experimental language model. Treat its personality as a simulation and its outputs as generated text.
|