Instructions to use Q-bert/Terminis-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Q-bert/Terminis-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Q-bert/Terminis-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Q-bert/Terminis-7B") model = AutoModelForCausalLM.from_pretrained("Q-bert/Terminis-7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Q-bert/Terminis-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Q-bert/Terminis-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Q-bert/Terminis-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Q-bert/Terminis-7B
- SGLang
How to use Q-bert/Terminis-7B 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 "Q-bert/Terminis-7B" \ --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": "Q-bert/Terminis-7B", "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 "Q-bert/Terminis-7B" \ --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": "Q-bert/Terminis-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Q-bert/Terminis-7B with Docker Model Runner:
docker model run hf.co/Q-bert/Terminis-7B
Commit ·
b60f97a
1
Parent(s): c3cde86
add merge tag
Browse filesTo make it easier to identify merge models, we're experimenting with adding a `merge` tag for models created via a merge.
README.md
CHANGED
|
@@ -3,7 +3,8 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
-
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
## Terminis-7B
|
|
@@ -24,5 +25,4 @@ Detailed results can be found [Coming soon]()
|
|
| 24 |
| MMLU (5-shot) | Coming soon |
|
| 25 |
| TruthfulQA (0-shot) | Coming soon |
|
| 26 |
| Winogrande (5-shot) | Coming soon |
|
| 27 |
-
| GSM8K (5-shot) | Coming soon |
|
| 28 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- merge
|
| 8 |
---
|
| 9 |
|
| 10 |
## Terminis-7B
|
|
|
|
| 25 |
| MMLU (5-shot) | Coming soon |
|
| 26 |
| TruthfulQA (0-shot) | Coming soon |
|
| 27 |
| Winogrande (5-shot) | Coming soon |
|
| 28 |
+
| GSM8K (5-shot) | Coming soon |
|
|
|