Text Generation
Transformers
Safetensors
English
pragya_e2
small-language-model
from-scratch
causal-lm
decoder-only
gqa
rope
swiglu
exclusive-gated-attention
engram
kv-cache
custom_code
Instructions to use RuVI-AI/Pragya-EXP2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RuVI-AI/Pragya-EXP2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RuVI-AI/Pragya-EXP2", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("RuVI-AI/Pragya-EXP2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RuVI-AI/Pragya-EXP2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RuVI-AI/Pragya-EXP2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RuVI-AI/Pragya-EXP2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RuVI-AI/Pragya-EXP2
- SGLang
How to use RuVI-AI/Pragya-EXP2 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 "RuVI-AI/Pragya-EXP2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RuVI-AI/Pragya-EXP2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "RuVI-AI/Pragya-EXP2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RuVI-AI/Pragya-EXP2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RuVI-AI/Pragya-EXP2 with Docker Model Runner:
docker model run hf.co/RuVI-AI/Pragya-EXP2
Delete tokenizer
Browse files
tokenizer/tokenizer.pkl
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0ca760f09eb2dd9e980654f61e75867c04f1a9afd9245a031a0fa50025b2bc88
|
| 3 |
-
size 147083
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer_config.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"vocab_size": 12288,
|
| 3 |
-
"bos_id": 12287,
|
| 4 |
-
"eos_id": 12287,
|
| 5 |
-
"pad_id": 12287,
|
| 6 |
-
"unk_id": 12287
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|