Instructions to use Intrinsic-Data/mistral7b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intrinsic-Data/mistral7b-base with Transformers:

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

pipe = pipeline("text-generation", model="Intrinsic-Data/mistral7b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intrinsic-Data/mistral7b-base")
model = AutoModelForCausalLM.from_pretrained("Intrinsic-Data/mistral7b-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intrinsic-Data/mistral7b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intrinsic-Data/mistral7b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intrinsic-Data/mistral7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Intrinsic-Data/mistral7b-base

SGLang

How to use Intrinsic-Data/mistral7b-base 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 "Intrinsic-Data/mistral7b-base" \
    --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": "Intrinsic-Data/mistral7b-base",
		"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 "Intrinsic-Data/mistral7b-base" \
        --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": "Intrinsic-Data/mistral7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intrinsic-Data/mistral7b-base with Docker Model Runner:
```
docker model run hf.co/Intrinsic-Data/mistral7b-base
```

Bam4d commited on Sep 26, 2023

Commit

0e5a0e2

1 Parent(s): 27f7f8c

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

tokenizer.json +0 -0
tokenizer_config.json +3 -3

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -5,7 +5,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,7 +21,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

     "0": {
       "content": "<unk>",
       "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     "1": {
       "content": "<s>",
       "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     "2": {
       "content": "</s>",
       "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true