Text Generation
Transformers
PyTorch
English
Chinese
llama
llama2
qwen
causallm
text-generation-inference
Instructions to use CausalLM/7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CausalLM/7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CausalLM/7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CausalLM/7B") model = AutoModelForCausalLM.from_pretrained("CausalLM/7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CausalLM/7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CausalLM/7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CausalLM/7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CausalLM/7B
- SGLang
How to use CausalLM/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 "CausalLM/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": "CausalLM/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 "CausalLM/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": "CausalLM/7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CausalLM/7B with Docker Model Runner:
docker model run hf.co/CausalLM/7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,11 +31,6 @@ tags:
|
|
| 31 |
- qwen
|
| 32 |
- causallm
|
| 33 |
---
|
| 34 |
-
**Sorry, it's no longer available on Hugging Face. Please reach out to those who have already downloaded it. If you have a copy, please refrain from re-uploading it to Hugging Face.**
|
| 35 |
-
|
| 36 |
-
**Due to repeated conflicts with HF and what we perceive as their repeated misuse of the "Contributor Covenant Code of Conduct," we have lost confidence in the platform and decided to temporarily suspend all new download access requests. It appears to us that HF's original intention has been abandoned in pursuit of commercialization, and they no longer prioritize the well-being of the community.**
|
| 37 |
-
|
| 38 |
-
|
| 39 |
[](https://causallm.org/)
|
| 40 |
|
| 41 |
*Image drawn by GPT-4 DALL路E 3* **TL;DR: Perhaps this 7B model, better than all existing models <= 33B, in most quantitative evaluations...**
|
|
|
|
| 31 |
- qwen
|
| 32 |
- causallm
|
| 33 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
[](https://causallm.org/)
|
| 35 |
|
| 36 |
*Image drawn by GPT-4 DALL路E 3* **TL;DR: Perhaps this 7B model, better than all existing models <= 33B, in most quantitative evaluations...**
|