Instructions to use greatakela/mistral_multiclass_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use greatakela/mistral_multiclass_full with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="greatakela/mistral_multiclass_full")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("greatakela/mistral_multiclass_full")
model = AutoModelForCausalLM.from_pretrained("greatakela/mistral_multiclass_full")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use greatakela/mistral_multiclass_full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "greatakela/mistral_multiclass_full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "greatakela/mistral_multiclass_full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/greatakela/mistral_multiclass_full

SGLang

How to use greatakela/mistral_multiclass_full 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 "greatakela/mistral_multiclass_full" \
    --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": "greatakela/mistral_multiclass_full",
		"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 "greatakela/mistral_multiclass_full" \
        --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": "greatakela/mistral_multiclass_full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use greatakela/mistral_multiclass_full with Docker Model Runner:
```
docker model run hf.co/greatakela/mistral_multiclass_full
```

Py: model = which model name?

by iza-alsa - opened Feb 23, 2024

Discussion

iza-alsa

Feb 23, 2024

I am trying to do some fine tuning on Mistral.
When defining a model in my notebook, how should I mention this model, or in general, models which don't have a Model Card?
Eg:
this is the line of code for another model:

model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=num_labels)

how do I know what to write to use this mistral_multicalss_full?

Thanks a lot,
and my apologies for what is probably a very silly question (AI beginner here..)

greatakela

Owner Feb 23, 2024

Iza-alsa, just put the name of the model (e.g. 'greatakela/mistral_multiclass_full') instead of 'bert-base-uncased'. The problem is, this particular model will inherit from Mistral models and would not support TFBertForSequenceClassification. Try MistralForSequenceClassification.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment