Instructions to use explosion-testing/mpt-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use explosion-testing/mpt-test with Transformers:

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

pipe = pipeline("text-generation", model="explosion-testing/mpt-test", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("explosion-testing/mpt-test", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("explosion-testing/mpt-test", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use explosion-testing/mpt-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/explosion-testing/mpt-test

SGLang

How to use explosion-testing/mpt-test 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 "explosion-testing/mpt-test" \
    --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": "explosion-testing/mpt-test",
		"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 "explosion-testing/mpt-test" \
        --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": "explosion-testing/mpt-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use explosion-testing/mpt-test with Docker Model Runner:
```
docker model run hf.co/explosion-testing/mpt-test
```

Daniël de Kok commited on Aug 7, 2023

Commit

1a52f36

1 Parent(s): d00224b

Add MPT test

Browse files

Files changed (3) hide show

config.json +30 -0
generation_config.json +5 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "architectures": [
+    "MptForCausalLM"
+  ],
+  "attn_config": {
+    "model_type": ""
+  },
+  "d_model": 32,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "init_device": "cpu",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "model_type": "mpt",
+  "n_heads": 4,
+  "n_layers": 5,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "num_key_value_heads": 2,
+  "resid_pdrop": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 1024
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "_from_model_config": true,
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": false
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b2337635ab3a4cb734bbca9f6476bc30ea7ede92189cdce3a932ec18ad6e1e
+size 388177