Text Generation
Transformers
Safetensors
English
Hindi
mixtral
agent
Qwen
AI
ST-X-0
MIXTRAL
TIGER OM
text-generation-inference
Instructions to use Shrijanagain/TIGER-OM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shrijanagain/TIGER-OM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Shrijanagain/TIGER-OM")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Shrijanagain/TIGER-OM") model = AutoModelForCausalLM.from_pretrained("Shrijanagain/TIGER-OM") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Shrijanagain/TIGER-OM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Shrijanagain/TIGER-OM" # 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-OM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Shrijanagain/TIGER-OM
- SGLang
How to use Shrijanagain/TIGER-OM 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-OM" \ --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-OM", "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-OM" \ --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-OM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Shrijanagain/TIGER-OM with Docker Model Runner:
docker model run hf.co/Shrijanagain/TIGER-OM
Upload mergekit_moe_config.yml with huggingface_hub
Browse files- mergekit_moe_config.yml +8 -0
mergekit_moe_config.yml
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
base_model: unsloth/mistral-7b-v0.3
|
| 3 |
+
gate_mode: random
|
| 4 |
+
dtype: bfloat16
|
| 5 |
+
experts:
|
| 6 |
+
- source_model: unsloth/mistral-7b-v0.3
|
| 7 |
+
- source_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 8 |
+
tokenizer_source: base_model
|