Text Generation
Transformers
Safetensors
Lithuanian
llama
blkt
causal-lm
pretraining
lithuanian
llama3
text-generation-inference
Instructions to use VSSA-SDSA/LT_AI_DLKVM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VSSA-SDSA/LT_AI_DLKVM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="VSSA-SDSA/LT_AI_DLKVM")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("VSSA-SDSA/LT_AI_DLKVM") model = AutoModelForMultimodalLM.from_pretrained("VSSA-SDSA/LT_AI_DLKVM") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use VSSA-SDSA/LT_AI_DLKVM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "VSSA-SDSA/LT_AI_DLKVM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "VSSA-SDSA/LT_AI_DLKVM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/VSSA-SDSA/LT_AI_DLKVM
- SGLang
How to use VSSA-SDSA/LT_AI_DLKVM 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 "VSSA-SDSA/LT_AI_DLKVM" \ --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": "VSSA-SDSA/LT_AI_DLKVM", "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 "VSSA-SDSA/LT_AI_DLKVM" \ --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": "VSSA-SDSA/LT_AI_DLKVM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use VSSA-SDSA/LT_AI_DLKVM with Docker Model Runner:
docker model run hf.co/VSSA-SDSA/LT_AI_DLKVM
Upload dvlkm.jsonld
Browse files- dvlkm.jsonld +84 -0
dvlkm.jsonld
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"@context": "https://semiceu.github.io/MLDCAT-AP/releases/3.0.0/context/mldcat-ap.jsonld",
|
| 3 |
+
"@type": "it6:MachineLearningModel",
|
| 4 |
+
"@id": "https://example.lt/model/DVLKM",
|
| 5 |
+
"dct:identifier": "DVLKM",
|
| 6 |
+
"dct:title": {
|
| 7 |
+
"@value": "LT generavimo modelis",
|
| 8 |
+
"@language": "lt"
|
| 9 |
+
},
|
| 10 |
+
"dct:description": {
|
| 11 |
+
"@value": "LT generavimo modelis",
|
| 12 |
+
"@language": "lt"
|
| 13 |
+
},
|
| 14 |
+
"dct:created": "2026-04-15 00:00:00",
|
| 15 |
+
"it6:version": "1.0",
|
| 16 |
+
"dct:publisher": {
|
| 17 |
+
"@type": "foaf:Agent",
|
| 18 |
+
"foaf:name": "VSSA"
|
| 19 |
+
},
|
| 20 |
+
"dct:creator": {
|
| 21 |
+
"@type": "foaf:Agent",
|
| 22 |
+
"foaf:name": "UAB Neurotechnology"
|
| 23 |
+
},
|
| 24 |
+
"dct:rightsHolder": {
|
| 25 |
+
"@type": "foaf:Agent",
|
| 26 |
+
"foaf:name": "VSSA"
|
| 27 |
+
},
|
| 28 |
+
"dct:license": {
|
| 29 |
+
"@id": "MIT"
|
| 30 |
+
},
|
| 31 |
+
"it6:intendedUse": [
|
| 32 |
+
{
|
| 33 |
+
"@value": "modelis skirtas teksyto generavimui",
|
| 34 |
+
"@language": "lt"
|
| 35 |
+
}
|
| 36 |
+
],
|
| 37 |
+
"dct:language": [
|
| 38 |
+
{
|
| 39 |
+
"@value": "lt"
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"it6:modelArchitecture": [
|
| 43 |
+
{
|
| 44 |
+
"@value": "transformer"
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"it6:hasInputModality": [
|
| 48 |
+
{
|
| 49 |
+
"@value": "text"
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"it6:hasOutputModality": [
|
| 53 |
+
{
|
| 54 |
+
"@value": "text"
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"dcat:landingPage": {
|
| 58 |
+
"@id": "Huggingface"
|
| 59 |
+
},
|
| 60 |
+
"it6:trainedOn": [
|
| 61 |
+
{
|
| 62 |
+
"@id": "https://example.lt/dataset/BLKT"
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"it6:hasFile": [
|
| 66 |
+
{
|
| 67 |
+
"@type": "it6:File",
|
| 68 |
+
"@id": "https://example.lt/file/dvlkm",
|
| 69 |
+
"dct:title": {
|
| 70 |
+
"@value": "DLKVM",
|
| 71 |
+
"@language": "lt"
|
| 72 |
+
},
|
| 73 |
+
"dct:format": {
|
| 74 |
+
"@value": "application/octet-stream"
|
| 75 |
+
},
|
| 76 |
+
"dcat:accessURL": {
|
| 77 |
+
"@id": "Huggingface"
|
| 78 |
+
},
|
| 79 |
+
"it6:url": {
|
| 80 |
+
"@id": "Huggingface"
|
| 81 |
+
}
|
| 82 |
+
}
|
| 83 |
+
]
|
| 84 |
+
}
|