Instructions to use yujiepan/mpt-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/mpt-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/mpt-tiny-random", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/mpt-tiny-random", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("yujiepan/mpt-tiny-random", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yujiepan/mpt-tiny-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yujiepan/mpt-tiny-random

SGLang

How to use yujiepan/mpt-tiny-random 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 "yujiepan/mpt-tiny-random" \
    --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": "yujiepan/mpt-tiny-random",
		"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 "yujiepan/mpt-tiny-random" \
        --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": "yujiepan/mpt-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yujiepan/mpt-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/mpt-tiny-random
```

yujiepan commited on Oct 29, 2023

Commit

1b510f2

1 Parent(s): 2d5dd51

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

config.json +3 -2
generation_config.json +1 -2
openvino_model.bin +3 -0
openvino_model.xml +0 -0
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "neuralmagic/mpt-7b-gsm8k-pt",
   "architectures": [
     "MptForCausalLM"
   ],
@@ -27,6 +27,7 @@
   },
   "init_device": "cpu",
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "learned_pos_emb": true,
   "logit_scale": null,
@@ -41,7 +42,7 @@
   "tokenizer_name": "EleutherAI/gpt-neox-20b",
   "torch_dtype": "float16",
   "transformers_version": "4.34.1",
-  "use_cache": false,
   "verbose": 0,
   "vocab_size": 50432
 }

 {
+  "_name_or_path": "/tmp/yujiepan/mpt-tiny-random/config.json",
   "architectures": [
     "MptForCausalLM"
   ],
   },
   "init_device": "cpu",
   "initializer_range": 0.02,
+  "is_decoder": true,
   "layer_norm_epsilon": 1e-05,
   "learned_pos_emb": true,
   "logit_scale": null,
   "tokenizer_name": "EleutherAI/gpt-neox-20b",
   "torch_dtype": "float16",
   "transformers_version": "4.34.1",
+  "use_cache": true,
   "verbose": 0,
   "vocab_size": 50432
 }

generation_config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.34.1",
-  "use_cache": false
 }

 {
   "_from_model_config": true,
+  "transformers_version": "4.34.1"
 }

openvino_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2d981f272bf256577fa3ba97a8c23f4975fb0f1b4f0b077419542e88c98d9827
+size 818595

openvino_model.xml ADDED Viewed

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

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ee22f0985c9c43eaa0b5a45b0ea8d018799ec0566998448e94d505a8e52a3c
 size 815064

 version https://git-lfs.github.com/spec/v1
+oid sha256:9b208d69cc632b6d306708b2eb8a884af0a3fd8454e660464e3431f7e2a256ba
 size 815064