Text Generation
Transformers
TensorBoard
Safetensors
gemma3_text
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use Jeganbaskar/snap-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jeganbaskar/snap-ai with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jeganbaskar/snap-ai") 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("Jeganbaskar/snap-ai") model = AutoModelForCausalLM.from_pretrained("Jeganbaskar/snap-ai", 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 Jeganbaskar/snap-ai with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jeganbaskar/snap-ai" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jeganbaskar/snap-ai", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Jeganbaskar/snap-ai
- SGLang
How to use Jeganbaskar/snap-ai 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 "Jeganbaskar/snap-ai" \ --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": "Jeganbaskar/snap-ai", "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 "Jeganbaskar/snap-ai" \ --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": "Jeganbaskar/snap-ai", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Jeganbaskar/snap-ai with Docker Model Runner:
docker model run hf.co/Jeganbaskar/snap-ai
Commit History
-
Training in progress, epoch 3
Verified signatureaa2be94 -
Training in progress, epoch 3
Verified signature8041fc2 -
Training in progress, epoch 3
Verified signature8f67d4f -
Training in progress, epoch 3
Verified signaturea710e76 -
Training in progress, epoch 3
Verified signature0711275
-
Training in progress, epoch 3
Verified signaturea0e70d7 -
Training in progress, epoch 5
Verified signaturec61d9f1 -
Model save
Verified signatured4653da -
Training in progress, epoch 5
Verified signaturee1faead
-
Training in progress, epoch 5
Verified signature3df430b -
Training in progress, epoch 3
Verified signature9ab290a -
Training in progress, epoch 5
Verified signaturec07ee56
-
Model save
Verified signature5edc14b -
Training in progress, epoch 15
Verified signature6b96c62 -
Training in progress, epoch 13
Verified signaturee180777 -
Training in progress, epoch 11
Verified signature77f791d -
Training in progress, epoch 9
Verified signaturef56ab15 -
Training in progress, epoch 5
Verified signature4c6fc22 -
Training in progress, epoch 4
Verified signature817b274 -
Training in progress, epoch 3
Verified signatureaf674a5 -
Training in progress, epoch 9
Verified signature9591efb -
Training in progress, epoch 6
Verified signatureddd9227 -
Training in progress, epoch 1
Verified signature548fa52 -
Training in progress, epoch 8
Verified signature387cd0a -
Training in progress, epoch 5
Verified signature87f21fe -
Training in progress, epoch 1
Verified signature0be6aac -
Training in progress, epoch 5
Verified signature5e15372 -
Training in progress, epoch 3
Verified signature40468ce -
Training in progress, epoch 1
Verified signatured735227 -
Model save
Verified signature797ebb8 -
Training in progress, epoch 13
Verified signaturea6b103d -
Training in progress, epoch 10
Verified signatureb7ba548 -
Training in progress, epoch 4
Verified signature7416996 -
Training in progress, epoch 3
Verified signature14f5c8e -
Training in progress, epoch 2
Verified signature35276e4 -
Training in progress, epoch 10
Verified signature9663a52 -
Training in progress, epoch 9
Verified signature810d33c -
Training in progress, epoch 7
Verified signature48a2fad -
Training in progress, epoch 4
Verified signature0f7f4dc -
Training in progress, epoch 3
Verified signature5775a0d -
Training in progress, epoch 2
Verified signaturee721594 -
Training in progress, epoch 1
Verified signature5b40b49 -
Training in progress, epoch 5
Verified signature935f785 -
Training in progress, epoch 4
Verified signaturede81f73 -
Training in progress, epoch 3
Verified signature3d8fd04 -
Training in progress, epoch 1
Verified signaturee175139 -
Model save
Verified signaturecd46c51 -
Model save
Verified signature323a212 -
Model save
Verified signaturedd4f082 -
Training in progress, epoch 5
Verified signaturef433164