Instructions to use CultriX/MistralTrix-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CultriX/MistralTrix-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CultriX/MistralTrix-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CultriX/MistralTrix-v1") model = AutoModelForCausalLM.from_pretrained("CultriX/MistralTrix-v1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CultriX/MistralTrix-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CultriX/MistralTrix-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CultriX/MistralTrix-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CultriX/MistralTrix-v1
- SGLang
How to use CultriX/MistralTrix-v1 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 "CultriX/MistralTrix-v1" \ --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": "CultriX/MistralTrix-v1", "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 "CultriX/MistralTrix-v1" \ --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": "CultriX/MistralTrix-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CultriX/MistralTrix-v1 with Docker Model Runner:
docker model run hf.co/CultriX/MistralTrix-v1
colab notebook.
#10 opened about 2 years ago
by
ZeroWw
Adding Evaluation Results
#9 opened about 2 years ago
by
leaderboard-pr-bot
This is not a 7B. It's a ~9B. Please label appropriately.
1
#7 opened over 2 years ago
by
georgewalker
Contaminated?
7
#6 opened over 2 years ago
by
kno10
Quantized 4x MoE of this model.
#5 opened over 2 years ago
by
Kquant03
Congrats and request for the source code
1
#4 opened over 2 years ago
by
Overbite1741
Congrats!
๐๐คฏ 9
10
#3 opened over 2 years ago
by
mlabonne
Missing ChatML tokens and unexpected symbols in the response
๐ 1
2
#2 opened over 2 years ago
by
Ont