Instructions to use NLUHOPOE/Mistral-test-case-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NLUHOPOE/Mistral-test-case-2 with Transformers:

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

pipe = pipeline("text-generation", model="NLUHOPOE/Mistral-test-case-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NLUHOPOE/Mistral-test-case-2")
model = AutoModelForCausalLM.from_pretrained("NLUHOPOE/Mistral-test-case-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NLUHOPOE/Mistral-test-case-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NLUHOPOE/Mistral-test-case-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NLUHOPOE/Mistral-test-case-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NLUHOPOE/Mistral-test-case-2

SGLang

How to use NLUHOPOE/Mistral-test-case-2 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 "NLUHOPOE/Mistral-test-case-2" \
    --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": "NLUHOPOE/Mistral-test-case-2",
		"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 "NLUHOPOE/Mistral-test-case-2" \
        --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": "NLUHOPOE/Mistral-test-case-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NLUHOPOE/Mistral-test-case-2 with Docker Model Runner:
```
docker model run hf.co/NLUHOPOE/Mistral-test-case-2
```

NLUHOPOE commited on Jan 26, 2024

Commit

b29a345

verified ·

1 Parent(s): 20006d9

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -1

README.md CHANGED Viewed

@@ -9,4 +9,22 @@ language:
 # Model Details
 * Model Description: This model is test for data ordering.
 * Developed by: Juhwan Lee
-* Model Type: Large Language Model

 # Model Details
 * Model Description: This model is test for data ordering.
 * Developed by: Juhwan Lee
+* Model Type: Large Language Model
+# Model Architecture
+This model is based on Mistral-7B-v0.1. We fine-tuning this model for data ordering task.
+Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
+* Grouped-Query Attention
+* Sliding-Window Attention
+* Byte-fallback BPE tokenizer
+# Dataset
+We random sample Open-Orca dataset. (We finetune the 100,000 dataset)
+# Guthub
+https://github.com/trailerAI
+# License
+Apache License 2.0