Instructions to use MetaIX/Guanaco-33B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MetaIX/Guanaco-33B-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MetaIX/Guanaco-33B-4bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MetaIX/Guanaco-33B-4bit") model = AutoModelForCausalLM.from_pretrained("MetaIX/Guanaco-33B-4bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MetaIX/Guanaco-33B-4bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MetaIX/Guanaco-33B-4bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MetaIX/Guanaco-33B-4bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MetaIX/Guanaco-33B-4bit
- SGLang
How to use MetaIX/Guanaco-33B-4bit 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 "MetaIX/Guanaco-33B-4bit" \ --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": "MetaIX/Guanaco-33B-4bit", "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 "MetaIX/Guanaco-33B-4bit" \ --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": "MetaIX/Guanaco-33B-4bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MetaIX/Guanaco-33B-4bit with Docker Model Runner:
docker model run hf.co/MetaIX/Guanaco-33B-4bit
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,8 +4,8 @@ Guanaco 33b working with Oobabooga's Text Generation Webui and KoboldAI.
|
|
| 4 |
|
| 5 |
<p><strong>What's included</strong></p>
|
| 6 |
|
| 7 |
-
<P>GPTQ: 2 quantized versions. One quantized --true-sequential and act-order optimizations, and the other was quantized using --true-sequential --groupsize 128 optimizations.</P>
|
| 8 |
-
<P>GGML: 3 quantized versions. One quantized using q4_1, another was quantized using q5_0, and the last one was quantized using q5_1.</P>
|
| 9 |
|
| 10 |
<p><strong>GPU/GPTQ Usage</strong></p>
|
| 11 |
<p>To use with your GPU using GPTQ pick one of the .safetensors along with all of the .jsons and .model files.</p>
|
|
|
|
| 4 |
|
| 5 |
<p><strong>What's included</strong></p>
|
| 6 |
|
| 7 |
+
<P>GPTQ: 2 quantized versions. One quantized --true-sequential and act-order optimizations, and the other was quantized using --true-sequential --groupsize 128 optimizations (coming soon).</P>
|
| 8 |
+
<P>GGML: 3 quantized versions. One quantized using q4_1 (coming soon), another was quantized using q5_0 (coming soon), and the last one was quantized using q5_1 (coming soon).</P>
|
| 9 |
|
| 10 |
<p><strong>GPU/GPTQ Usage</strong></p>
|
| 11 |
<p>To use with your GPU using GPTQ pick one of the .safetensors along with all of the .jsons and .model files.</p>
|