Instructions to use typeof/MistralLite-sharded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typeof/MistralLite-sharded with Transformers:

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

pipe = pipeline("text-generation", model="typeof/MistralLite-sharded")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("typeof/MistralLite-sharded")
model = AutoModelForCausalLM.from_pretrained("typeof/MistralLite-sharded")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use typeof/MistralLite-sharded with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/typeof/MistralLite-sharded

SGLang

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

Docker Model Runner
How to use typeof/MistralLite-sharded with Docker Model Runner:
```
docker model run hf.co/typeof/MistralLite-sharded
```

typeof commited on Nov 23, 2023

Commit

5df5e4d

1 Parent(s): 96035bb

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -5,6 +5,11 @@ inference: false
 # MistralLite Model
 MistralLite is a fine-tuned [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) language model, with enhanced capabilities of processing long context (up to 32K tokens). By utilizing an adapted Rotary Embedding and sliding window during fine-tuning, MistralLite is able to **perform significantly better on several long context retrieve and answering tasks**, while keeping the simple model structure of the original model. MistralLite is useful for applications such as long context line and topic retrieval, summarization, question-answering, and etc. MistralLite can be deployed on a single AWS `g5.2x` instance with Sagemaker [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) endpoint, making it suitable for applications that require high performance in resource-constrained environments. You can also serve the MistralLite model directly using TGI docker containers. Also, MistralLite supports other ways of serving like [vLLM](https://github.com/vllm-project/vllm), and you can use MistralLite in Python by using the [HuggingFace transformers](https://huggingface.co/docs/transformers/index) and [FlashAttention-2](https://github.com/Dao-AILab/flash-attention) library.
 MistralLite is similar to [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), and their similarities and differences are summarized below:

 # MistralLite Model
+## This is the sharded version of https://huggingface.co/amazon/MistralLite
+### Most recent commit [2348608](https://huggingface.co/amazon/MistralLite/commit/23486089ab7ba741b34adc69ab7555885f8abe71)
 MistralLite is a fine-tuned [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) language model, with enhanced capabilities of processing long context (up to 32K tokens). By utilizing an adapted Rotary Embedding and sliding window during fine-tuning, MistralLite is able to **perform significantly better on several long context retrieve and answering tasks**, while keeping the simple model structure of the original model. MistralLite is useful for applications such as long context line and topic retrieval, summarization, question-answering, and etc. MistralLite can be deployed on a single AWS `g5.2x` instance with Sagemaker [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) endpoint, making it suitable for applications that require high performance in resource-constrained environments. You can also serve the MistralLite model directly using TGI docker containers. Also, MistralLite supports other ways of serving like [vLLM](https://github.com/vllm-project/vllm), and you can use MistralLite in Python by using the [HuggingFace transformers](https://huggingface.co/docs/transformers/index) and [FlashAttention-2](https://github.com/Dao-AILab/flash-attention) library.
 MistralLite is similar to [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), and their similarities and differences are summarized below: