Text Generation
Transformers
PyTorch
Safetensors
English
llama
text-generation-inference
unsloth
trl
sft
conversational
Instructions to use T3lli/HumanDialogue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use T3lli/HumanDialogue with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="T3lli/HumanDialogue") 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("T3lli/HumanDialogue") model = AutoModelForCausalLM.from_pretrained("T3lli/HumanDialogue", 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 T3lli/HumanDialogue with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "T3lli/HumanDialogue" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "T3lli/HumanDialogue", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/T3lli/HumanDialogue
- SGLang
How to use T3lli/HumanDialogue 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 "T3lli/HumanDialogue" \ --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": "T3lli/HumanDialogue", "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 "T3lli/HumanDialogue" \ --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": "T3lli/HumanDialogue", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use T3lli/HumanDialogue with Docker Model Runner:
docker model run hf.co/T3lli/HumanDialogue
Commit History
-
Trained with Unsloth
Verified signature5a394e1 -
Upload tokenizer
Verified signaturebdaae77 -
Update README.md
Verified signature4aafc7e
-
Trained with Unsloth
Verified signature084f0f5 -
Upload tokenizer
Verified signature0f1f9c0 -
Training in progress, step 4671
Verified signatureac0ea09 -
Training in progress, step 4500
Verified signature26f824b -
Training in progress, step 4250
Verified signature3103392 -
Training in progress, step 4000
Verified signature84be9b9 -
Training in progress, step 3750
Verified signatureba79015 -
Training in progress, step 3500
Verified signature02c2a47 -
Training in progress, step 3250
Verified signature9a3ab9d -
Training in progress, step 3000
Verified signature7f0d2db -
Training in progress, step 2750
Verified signature04a1b75 -
Training in progress, step 2500
Verified signature88dfb77 -
Training in progress, step 2250
Verified signaturec5bf014 -
Training in progress, step 2000
Verified signaturea960ef2 -
Training in progress, step 1750
Verified signaturec205c81 -
Training in progress, step 1500
Verified signaturea154abf -
Training in progress, step 1250
Verified signature163392c -
Training in progress, step 1000
Verified signature9d99bbd -
Training in progress, step 750
Verified signature1249e58 -
Training in progress, step 500
Verified signature9588566 -
Training in progress, step 250
Verified signature87d1073 -
initial commit
Verified signature56546ab