Text Generation
Transformers
Safetensors
Bengali
English
llama
text-generation-inference
Eval Results (legacy)
Instructions to use Polygl0t/LilTii-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Polygl0t/LilTii-v0.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Polygl0t/LilTii-v0.2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Polygl0t/LilTii-v0.2") model = AutoModelForCausalLM.from_pretrained("Polygl0t/LilTii-v0.2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Polygl0t/LilTii-v0.2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Polygl0t/LilTii-v0.2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Polygl0t/LilTii-v0.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Polygl0t/LilTii-v0.2
- SGLang
How to use Polygl0t/LilTii-v0.2 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 "Polygl0t/LilTii-v0.2" \ --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": "Polygl0t/LilTii-v0.2", "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 "Polygl0t/LilTii-v0.2" \ --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": "Polygl0t/LilTii-v0.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Polygl0t/LilTii-v0.2 with Docker Model Runner:
docker model run hf.co/Polygl0t/LilTii-v0.2
Upload folder using huggingface_hub
Browse files- .gitattributes +14 -0
- plots/aggregate_npm.png +3 -0
- plots/arc_challenge.png +3 -0
- plots/bangla_mmlu.png +3 -0
- plots/boolq-bn.png +3 -0
- plots/commonsenseqa-bn.png +3 -0
- plots/gradient_statistics_v1.png +3 -0
- plots/gradient_statistics_v2.png +3 -0
- plots/hellaswag.png +3 -0
- plots/learning_curves.png +3 -0
- plots/mmlu.png +3 -0
- plots/openbookqa-bn.png +3 -0
- plots/performance_vs_compute.png +3 -0
- plots/piqa-bn.png +3 -0
- plots/truthfulqa_mc1.png +3 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,17 @@ aggregate_npm.png filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
learning_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
performance_vs_compute.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
benchmarks.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
learning_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
performance_vs_compute.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
benchmarks.png filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
plots/aggregate_npm.png filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
plots/arc_challenge.png filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
plots/bangla_mmlu.png filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
plots/boolq-bn.png filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
plots/commonsenseqa-bn.png filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
plots/gradient_statistics_v1.png filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
plots/gradient_statistics_v2.png filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
plots/hellaswag.png filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
plots/learning_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
plots/mmlu.png filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
plots/openbookqa-bn.png filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
plots/performance_vs_compute.png filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
plots/piqa-bn.png filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
plots/truthfulqa_mc1.png filter=lfs diff=lfs merge=lfs -text
|
plots/aggregate_npm.png
ADDED
|
Git LFS Details
|
plots/arc_challenge.png
ADDED
|
Git LFS Details
|
plots/bangla_mmlu.png
ADDED
|
Git LFS Details
|
plots/boolq-bn.png
ADDED
|
Git LFS Details
|
plots/commonsenseqa-bn.png
ADDED
|
Git LFS Details
|
plots/gradient_statistics_v1.png
ADDED
|
Git LFS Details
|
plots/gradient_statistics_v2.png
ADDED
|
Git LFS Details
|
plots/hellaswag.png
ADDED
|
Git LFS Details
|
plots/learning_curves.png
ADDED
|
Git LFS Details
|
plots/mmlu.png
ADDED
|
Git LFS Details
|
plots/openbookqa-bn.png
ADDED
|
Git LFS Details
|
plots/performance_vs_compute.png
ADDED
|
Git LFS Details
|
plots/piqa-bn.png
ADDED
|
Git LFS Details
|
plots/truthfulqa_mc1.png
ADDED
|
Git LFS Details
|