Instructions to use normalcomputing/extended-mind-mpt-30b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use normalcomputing/extended-mind-mpt-30b-chat with Transformers:

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

pipe = pipeline("text-generation", model="normalcomputing/extended-mind-mpt-30b-chat", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("normalcomputing/extended-mind-mpt-30b-chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use normalcomputing/extended-mind-mpt-30b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "normalcomputing/extended-mind-mpt-30b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-mpt-30b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/normalcomputing/extended-mind-mpt-30b-chat

SGLang

How to use normalcomputing/extended-mind-mpt-30b-chat 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 "normalcomputing/extended-mind-mpt-30b-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-mpt-30b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "normalcomputing/extended-mind-mpt-30b-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-mpt-30b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use normalcomputing/extended-mind-mpt-30b-chat with Docker Model Runner:
```
docker model run hf.co/normalcomputing/extended-mind-mpt-30b-chat
```

phoebeklett commited on May 30, 2024

Commit

258c898

verified ·

1 Parent(s): 3ae9dd7

Update config.json

Browse files

Files changed (1) hide show

config.json +19 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mosaicml/mpt-30b-chat",
   "architectures": [
     "ExtendedMptForCausalLM"
   ],
@@ -7,8 +7,8 @@
     "model_type": ""
   },
   "auto_map": {
-    "AutoConfig": "mosaicml/mpt-30b-chat--configuration_mpt.MPTConfig",
-    "AutoModelForCausalLM": "mosaicml/mpt-30b-chat--modeling_mpt.MPTForCausalLM"
   },
   "d_model": 7168,
   "emb_pdrop": 0,
@@ -75,6 +75,22 @@
     true,
     true,
     true,
     true
   ],
   "verbose": 0,

 {
+  "_name_or_path": "normalcomputing/extended-mind-mpt-30b-chat",
   "architectures": [
     "ExtendedMptForCausalLM"
   ],
     "model_type": ""
   },
   "auto_map": {
+    "AutoConfig": "configuration.MptConfig",
+    "AutoModelForCausalLM": "modeling.MptForCausalLM"
   },
   "d_model": 7168,
   "emb_pdrop": 0,
     true,
     true,
     true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
+    true,
     true
   ],
   "verbose": 0,