Instructions to use AdoCleanCode/llasa_stage2_trained_multilingual_stage5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdoCleanCode/llasa_stage2_trained_multilingual_stage5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdoCleanCode/llasa_stage2_trained_multilingual_stage5") 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("AdoCleanCode/llasa_stage2_trained_multilingual_stage5") model = AutoModelForCausalLM.from_pretrained("AdoCleanCode/llasa_stage2_trained_multilingual_stage5", 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 AdoCleanCode/llasa_stage2_trained_multilingual_stage5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdoCleanCode/llasa_stage2_trained_multilingual_stage5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdoCleanCode/llasa_stage2_trained_multilingual_stage5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AdoCleanCode/llasa_stage2_trained_multilingual_stage5
- SGLang
How to use AdoCleanCode/llasa_stage2_trained_multilingual_stage5 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 "AdoCleanCode/llasa_stage2_trained_multilingual_stage5" \ --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": "AdoCleanCode/llasa_stage2_trained_multilingual_stage5", "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 "AdoCleanCode/llasa_stage2_trained_multilingual_stage5" \ --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": "AdoCleanCode/llasa_stage2_trained_multilingual_stage5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AdoCleanCode/llasa_stage2_trained_multilingual_stage5 with Docker Model Runner:
docker model run hf.co/AdoCleanCode/llasa_stage2_trained_multilingual_stage5
Commit History
-
Auto-upload after eval at step 20500 (eval_loss: 6.7276)
Verified signature3bc8a4a -
Auto-upload after eval at step 20000 (eval_loss: 6.7298)
Verified signature9fb3f93 -
Auto-upload after eval at step 19500 (eval_loss: 6.7324)
Verified signature6524f6d -
Auto-upload after eval at step 19000 (eval_loss: 6.7329)
Verified signature31a5f27 -
Auto-upload after eval at step 18500 (eval_loss: 6.7333)
Verified signatured7674c5 -
Auto-upload after eval at step 18000 (eval_loss: 6.7342)
Verified signature1b271c4 -
Auto-upload after eval at step 17500 (eval_loss: 6.7355)
Verified signaturec45e2ed -
Auto-upload after eval at step 17000 (eval_loss: 6.7356)
Verified signature78941d3 -
Auto-upload after eval at step 16500 (eval_loss: 6.7368)
Verified signature89c08b5 -
Auto-upload after eval at step 16000 (eval_loss: 6.7363)
Verified signature904e590 -
Auto-upload after eval at step 15500 (eval_loss: 6.7373)
Verified signature2a5dd99 -
Auto-upload after eval at step 15000 (eval_loss: 6.7376)
Verified signaturedcec247 -
Auto-upload after eval at step 14500 (eval_loss: 6.7354)
Verified signaturec97715b -
Auto-upload after eval at step 14000 (eval_loss: 6.7392)
Verified signaturea5dffbe -
Auto-upload after eval at step 13500 (eval_loss: 6.7433)
Verified signature75a40a4 -
Auto-upload after eval at step 13000 (eval_loss: 6.7414)
Verified signature37022c2 -
Auto-upload after eval at step 12500 (eval_loss: 6.7437)
Verified signature8bbfba0 -
Auto-upload after eval at step 12000 (eval_loss: 6.7442)
Verified signature962dad4 -
Auto-upload after eval at step 11500 (eval_loss: 6.7472)
Verified signaturee309a98 -
Auto-upload after eval at step 11000 (eval_loss: 6.7473)
Verified signature7f08296 -
Auto-upload after eval at step 10500 (eval_loss: 6.7514)
Verified signature4bbfe48 -
Auto-upload after eval at step 10000 (eval_loss: 6.7520)
Verified signature5aece2c -
Auto-upload after eval at step 9500 (eval_loss: 6.7533)
Verified signature6fb22f4 -
Auto-upload after eval at step 9000 (eval_loss: 6.7541)
Verified signaturef9c9d0e -
Auto-upload after eval at step 8500 (eval_loss: 6.7545)
Verified signature93fcf51 -
Auto-upload after eval at step 8000 (eval_loss: 6.7572)
Verified signature6e8eaa1 -
Auto-upload after eval at step 7500 (eval_loss: 6.7619)
Verified signature9a6ebf1 -
Auto-upload after eval at step 7000 (eval_loss: 6.7633)
Verified signature07311ec -
Auto-upload after eval at step 6500 (eval_loss: 6.7663)
Verified signature56430dd
-
Auto-upload after eval at step 6000 (eval_loss: 6.7664)
Verified signature361cee9 -
Auto-upload after eval at step 5500 (eval_loss: 6.7689)
Verified signature512783f -
Auto-upload after eval at step 5000 (eval_loss: 6.7711)
Verified signature31e9234 -
Auto-upload after eval at step 4500 (eval_loss: 6.7760)
Verified signature3153408 -
Auto-upload after eval at step 4000 (eval_loss: 6.7789)
Verified signatureb71b463 -
Auto-upload after eval at step 3500 (eval_loss: 6.7859)
Verified signature558dfc9 -
Auto-upload after eval at step 3000 (eval_loss: 6.7900)
Verified signature82d4559 -
Auto-upload after eval at step 2500 (eval_loss: 6.7998)
Verified signature850d281 -
Auto-upload after eval at step 2000 (eval_loss: 6.8042)
Verified signature73e83ac -
Auto-upload after eval at step 1500 (eval_loss: 6.8192)
Verified signature7160a61 -
Auto-upload after eval at step 1000 (eval_loss: 6.8228)
Verified signature93709c0 -
Auto-upload tokenizer after eval at step 500
Verified signaturee71c2e8 -
Auto-upload after eval at step 500 (eval_loss: 6.8158)
Verified signature62422d2 -
initial commit
Verified signature04239df