Instructions to use Shrijanagain/TIGER-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shrijanagain/TIGER-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Shrijanagain/TIGER-GGUF")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Shrijanagain/TIGER-GGUF", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Shrijanagain/TIGER-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Shrijanagain/TIGER-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Shrijanagain/TIGER-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Shrijanagain/TIGER-GGUF
- SGLang
How to use Shrijanagain/TIGER-GGUF 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 "Shrijanagain/TIGER-GGUF" \ --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": "Shrijanagain/TIGER-GGUF", "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 "Shrijanagain/TIGER-GGUF" \ --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": "Shrijanagain/TIGER-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Shrijanagain/TIGER-GGUF with Docker Model Runner:
docker model run hf.co/Shrijanagain/TIGER-GGUF
Update metadata (general.architecture, general.name, tokenizer.ggml.model)
Browse filesUpdated metadata:
* **general.architecture**: SKT-AI-LABS
* **general.name**: TIGER PASS 13B MIXTRAL
* **tokenizer.ggml.model**: MISTRAL
tiger-pass-v1-archive-q4_k_m.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7786978336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:802d2cb5a85bba2f81a4af243dfdf0e35efa47c97960d644cb72aecc81973331
|
| 3 |
size 7786978336
|