Instructions to use huypn16/MetaMath-DeepSeekMath-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huypn16/MetaMath-DeepSeekMath-7B with Transformers:

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

pipe = pipeline("text-generation", model="huypn16/MetaMath-DeepSeekMath-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huypn16/MetaMath-DeepSeekMath-7B")
model = AutoModelForCausalLM.from_pretrained("huypn16/MetaMath-DeepSeekMath-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huypn16/MetaMath-DeepSeekMath-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huypn16/MetaMath-DeepSeekMath-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huypn16/MetaMath-DeepSeekMath-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huypn16/MetaMath-DeepSeekMath-7B

SGLang

How to use huypn16/MetaMath-DeepSeekMath-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 "huypn16/MetaMath-DeepSeekMath-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": "huypn16/MetaMath-DeepSeekMath-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 "huypn16/MetaMath-DeepSeekMath-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": "huypn16/MetaMath-DeepSeekMath-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huypn16/MetaMath-DeepSeekMath-7B with Docker Model Runner:
```
docker model run hf.co/huypn16/MetaMath-DeepSeekMath-7B
```

huypn16 commited on May 28, 2024

Commit

07948e5

verified ·

1 Parent(s): 4845f30

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1
special_tokens_map.json +0 -7
tokenizer.json +1 -1
tokenizer_config.json +1 -2

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee958f7d2fddee1e68541aad4c5b057be89e9bcc75965eae60098a59cb96796
 size 4987202208

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e4c7122085a561213192d488999c3946d01126c5b9cf247a27926b7814d9387
 size 4987202208

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcb6c750e49ddca0b8a9cd48a0ede62b8313c2a42fee4e1bf7f74f8f65822a2
 size 4980945440

 version https://git-lfs.github.com/spec/v1
+oid sha256:38bc5bd2d7b66d884e0445316d3a11aa6c6d48e5cf896f069bb2f7ad480cea40
 size 4980945440

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23011510ff83cc3119d1afc397753fc790618c9bfcb2dfd752a5de864949eb9
 size 3852615520

 version https://git-lfs.github.com/spec/v1
+oid sha256:81f380b00371672dfc0d043e3d0bc1f82829586e435bb4fb5db1ef65bb28111c
 size 3852615520

special_tokens_map.json CHANGED Viewed

@@ -19,12 +19,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
   }
 }

     "normalized": false,
     "rstrip": false,
     "single_word": false
   }
 }

tokenizer.json CHANGED Viewed

@@ -32,7 +32,7 @@
     },
     {
       "id": 100003,
-      "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

     },
     {
       "id": 100003,
+      "content": "[STEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json CHANGED Viewed

@@ -27,7 +27,7 @@
       "special": true
     },
     "100003": {
-      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,7 +41,6 @@
   "legacy": true,
   "model_max_length": 4096,
   "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,

       "special": true
     },
     "100003": {
+      "content": "[STEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
   "legacy": true,
   "model_max_length": 4096,
   "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,