Instructions to use 64bits/LexPodLM-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 64bits/LexPodLM-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="64bits/LexPodLM-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("64bits/LexPodLM-13B") model = AutoModelForCausalLM.from_pretrained("64bits/LexPodLM-13B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use 64bits/LexPodLM-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "64bits/LexPodLM-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "64bits/LexPodLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/64bits/LexPodLM-13B
- SGLang
How to use 64bits/LexPodLM-13B 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 "64bits/LexPodLM-13B" \ --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": "64bits/LexPodLM-13B", "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 "64bits/LexPodLM-13B" \ --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": "64bits/LexPodLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 64bits/LexPodLM-13B with Docker Model Runner:
docker model run hf.co/64bits/LexPodLM-13B
Adding Evaluation Results
#2
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -44,4 +44,17 @@ Eval (evaluate models like [Open LLM Leaderboard](https://huggingface.co/spaces/
|
|
| 44 |
|
| 45 |
*Human: What are your thoughts on the Singularity theory?*
|
| 46 |
|
| 47 |
-
*Assistant: I am a strong proponent of the singularity. I have seen many technological advancements in my career. I've seen the power of exponential growth in technology. I've seen the power of exponential growth in markets, in the economy, and in population. And I'm very excited about the future. I'm very excited about what's going to happen. And I think that it's important for the world to understand that. And so I think that the singularity is very important for our future and we need to make sure that we're preparing for it.*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
*Human: What are your thoughts on the Singularity theory?*
|
| 46 |
|
| 47 |
+
*Assistant: I am a strong proponent of the singularity. I have seen many technological advancements in my career. I've seen the power of exponential growth in technology. I've seen the power of exponential growth in markets, in the economy, and in population. And I'm very excited about the future. I'm very excited about what's going to happen. And I think that it's important for the world to understand that. And so I think that the singularity is very important for our future and we need to make sure that we're preparing for it.*
|
| 48 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 49 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_64bits__LexPodLM-13B)
|
| 50 |
+
|
| 51 |
+
| Metric | Value |
|
| 52 |
+
|-----------------------|---------------------------|
|
| 53 |
+
| Avg. | 49.51 |
|
| 54 |
+
| ARC (25-shot) | 57.76 |
|
| 55 |
+
| HellaSwag (10-shot) | 81.04 |
|
| 56 |
+
| MMLU (5-shot) | 48.38 |
|
| 57 |
+
| TruthfulQA (0-shot) | 43.48 |
|
| 58 |
+
| Winogrande (5-shot) | 76.16 |
|
| 59 |
+
| GSM8K (5-shot) | 0.0 |
|
| 60 |
+
| DROP (3-shot) | 39.71 |
|