Instructions to use Writer/camel-5b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Writer/camel-5b-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Writer/camel-5b-hf")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Writer/camel-5b-hf") model = AutoModelForCausalLM.from_pretrained("Writer/camel-5b-hf") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Writer/camel-5b-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Writer/camel-5b-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Writer/camel-5b-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Writer/camel-5b-hf
- SGLang
How to use Writer/camel-5b-hf 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 "Writer/camel-5b-hf" \ --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": "Writer/camel-5b-hf", "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 "Writer/camel-5b-hf" \ --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": "Writer/camel-5b-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Writer/camel-5b-hf with Docker Model Runner:
docker model run hf.co/Writer/camel-5b-hf
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,12 +17,16 @@ img {
|
|
| 17 |
}
|
| 18 |
</style>
|
| 19 |
|
| 20 |
-
<img src="https://i.postimg.cc/wjXZLQbB/Camel-Llama.png" width="400px" />
|
| 21 |
-
|
| 22 |
|
| 23 |
## Model Description
|
| 24 |
|
| 25 |
-
Camel-5b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
|
| 28 |
|
|
|
|
| 17 |
}
|
| 18 |
</style>
|
| 19 |
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model Description
|
| 22 |
|
| 23 |
+
Introducing Camel-5b, a highly trained large language model that not only follows instructions but does so with the grace of a llama inspired by Mate. Imagine the elegance of a llama frolicking through the Andes, and that's what Camel-5b brings to the table.
|
| 24 |
+
|
| 25 |
+
Built upon the majestic foundation of [Palmyra-Base](https://huggingface.co/Writer/palmyra-base), Camel-5b has mastered the art of brainstorming, classification, closed quality assurance, generation, information extraction, open quality assurance, and summarization. All thanks to ~70k instruction & response fine-tuning records carefully crafted by the Writer Team from the InstructGPT paper.
|
| 26 |
+
|
| 27 |
+
But beware, dear reader! The Camel-5b Community is an exclusive club (license: Apache-2.0), limited by choice through a very strict license. After all, not everyone is ready for the llama-inspired linguistic prowess of Camel-5b! Join us, if you dare, and experience the whimsical wonder of witty wordplay!
|
| 28 |
+
|
| 29 |
+
<img src="https://i.postimg.cc/wjXZLQbB/Camel-Llama.png" width="400px" />
|
| 30 |
|
| 31 |
|
| 32 |
|