Instructions to use normalcomputing/extended-mind-mpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use normalcomputing/extended-mind-mpt-7b with Transformers:

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

pipe = pipeline("text-generation", model="normalcomputing/extended-mind-mpt-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("normalcomputing/extended-mind-mpt-7b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use normalcomputing/extended-mind-mpt-7b 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-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/normalcomputing/extended-mind-mpt-7b

SGLang

How to use normalcomputing/extended-mind-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 "normalcomputing/extended-mind-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": "normalcomputing/extended-mind-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 "normalcomputing/extended-mind-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": "normalcomputing/extended-mind-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use normalcomputing/extended-mind-mpt-7b with Docker Model Runner:
```
docker model run hf.co/normalcomputing/extended-mind-mpt-7b
```

Pklett commited on Oct 22, 2023

Commit

ac9e251

2 Parent(s): 90f88b7 c0a2dea

Merge branch 'main' of https://huggingface.co/normalcomputing/extended-mind-mpt-7b into main

Browse files

Files changed (3) hide show

blocks.py +1 -1
config.json +2 -2
modeling_mpt.py +4 -4

blocks.py CHANGED Viewed

@@ -7,7 +7,7 @@
 from typing import Dict, Optional, Tuple
 import torch
 import torch.nn as nn
-from memorizing_transformers.mpt.attention import ATTN_CLASS_REGISTRY
 from llmfoundry.models.layers.norm import NORM_CLASS_REGISTRY
 class MPTMLP(nn.Module):

 from typing import Dict, Optional, Tuple
 import torch
 import torch.nn as nn
+from attention import ATTN_CLASS_REGISTRY
 from llmfoundry.models.layers.norm import NORM_CLASS_REGISTRY
 class MPTMLP(nn.Module):

config.json CHANGED Viewed

@@ -21,8 +21,8 @@
     "use_active_externalism": true
   },
   "auto_map": {
-    "AutoConfig": "mosaicml/mpt-7b--configuration_mpt.MPTConfig",
-    "AutoModelForCausalLM": "mosaicml/mpt-7b--modeling_mpt.MPTForCausalLM"
   },
   "d_model": 4096,
   "emb_pdrop": 0,

     "use_active_externalism": true
   },
   "auto_map": {
+    "AutoConfig": "configuration.ExtendedMPTConfig",
+    "AutoModelForCausalLM": "modeling_mpt.ExtendedMPTForCausalLM"
   },
   "d_model": 4096,
   "emb_pdrop": 0,

modeling_mpt.py CHANGED Viewed

@@ -27,10 +27,10 @@ from llmfoundry.models.layers.custom_embedding import SharedEmbedding
 from llmfoundry.models.layers.norm import NORM_CLASS_REGISTRY
 from llmfoundry.models.utils.param_init_fns import MODEL_INIT_REGISTRY
-from memorizing_transformers.mpt.configuration import ExtendedMPTConfig
-from memorizing_transformers.mpt.attention import attn_bias_shape, build_attn_bias
-from memorizing_transformers.mpt.blocks import MPTBlock
-from memorizing_transformers.utils import instantiate_from_config
 Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]

 from llmfoundry.models.layers.norm import NORM_CLASS_REGISTRY
 from llmfoundry.models.utils.param_init_fns import MODEL_INIT_REGISTRY
+from configuration import ExtendedMPTConfig
+from attention import attn_bias_shape, build_attn_bias
+from blocks import MPTBlock
+from utils import instantiate_from_config
 Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]