Instructions to use Multi-Domain-Expert-Learning/given-mpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/given-mpt-7b with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/given-mpt-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/given-mpt-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/given-mpt-7b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/given-mpt-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Multi-Domain-Expert-Learning/given-mpt-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Multi-Domain-Expert-Learning/given-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/given-mpt-7b

SGLang

How to use Multi-Domain-Expert-Learning/given-mpt-7b 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 "Multi-Domain-Expert-Learning/given-mpt-7b" \
    --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": "Multi-Domain-Expert-Learning/given-mpt-7b",
		"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 "Multi-Domain-Expert-Learning/given-mpt-7b" \
        --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": "Multi-Domain-Expert-Learning/given-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/given-mpt-7b with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/given-mpt-7b
```

Ontocord.AI commited on Jun 27, 2023

Commit

f28a2f8

1 Parent(s): 067de39

Upload MPTForCausalLM

Browse files

Files changed (2) hide show

config.json +4 -3
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "architectures": [
     "MPTForCausalLM"
   ],
@@ -15,8 +16,8 @@
     "softmax_scale": null
   },
   "auto_map": {
-    "AutoConfig": "configuration_mpt.MPTConfig",
-    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
   },
   "d_model": 4096,
   "emb_pdrop": 0,
@@ -45,7 +46,7 @@
   "resid_pdrop": 0,
   "tokenizer_name": "EleutherAI/gpt-neox-20b",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.28.1",
   "use_cache": false,
   "verbose": 0,
   "vocab_size": 50432

 {
+  "_name_or_path": "TehVenom/MPT-7b-WizardLM_Uncensored-Storywriter-Merge",
   "architectures": [
     "MPTForCausalLM"
   ],
     "softmax_scale": null
   },
   "auto_map": {
+    "AutoConfig": "TehVenom/MPT-7b-WizardLM_Uncensored-Storywriter-Merge--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "TehVenom/MPT-7b-WizardLM_Uncensored-Storywriter-Merge--modeling_mpt.MPTForCausalLM"
   },
   "d_model": 4096,
   "emb_pdrop": 0,
   "resid_pdrop": 0,
   "tokenizer_name": "EleutherAI/gpt-neox-20b",
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.1",
   "use_cache": false,
   "verbose": 0,
   "vocab_size": 50432

generation_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.28.1",
   "use_cache": false
 }

 {
   "_from_model_config": true,
+  "transformers_version": "4.30.1",
   "use_cache": false
 }