Instructions to use typeof/all-MiniLM-L6-v2-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typeof/all-MiniLM-L6-v2-decoder with Transformers:

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

pipe = pipeline("text-generation", model="typeof/all-MiniLM-L6-v2-decoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("typeof/all-MiniLM-L6-v2-decoder")
model = AutoModelForCausalLM.from_pretrained("typeof/all-MiniLM-L6-v2-decoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use typeof/all-MiniLM-L6-v2-decoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typeof/all-MiniLM-L6-v2-decoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/all-MiniLM-L6-v2-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/typeof/all-MiniLM-L6-v2-decoder

SGLang

How to use typeof/all-MiniLM-L6-v2-decoder 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 "typeof/all-MiniLM-L6-v2-decoder" \
    --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": "typeof/all-MiniLM-L6-v2-decoder",
		"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 "typeof/all-MiniLM-L6-v2-decoder" \
        --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": "typeof/all-MiniLM-L6-v2-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use typeof/all-MiniLM-L6-v2-decoder with Docker Model Runner:
```
docker model run hf.co/typeof/all-MiniLM-L6-v2-decoder
```

typeof commited on Jun 15, 2024

Commit

62fd940

1 Parent(s): ae303c9

init

Browse files

Files changed (1) hide show

tokenizer.json +1 -76

tokenizer.json CHANGED Viewed

@@ -59,81 +59,6 @@
   "pre_tokenizer": {
     "type": "BertPreTokenizer"
   },
-  "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "[CLS]": {
-        "id": "[CLS]",
-        "ids": [
-          101
-        ],
-        "tokens": [
-          "[CLS]"
-        ]
-      },
-      "[SEP]": {
-        "id": "[SEP]",
-        "ids": [
-          102
-        ],
-        "tokens": [
-          "[SEP]"
-        ]
-      }
-    }
-  },
   "decoder": {
     "type": "WordPiece",
     "prefix": "##",
@@ -146,7 +71,7 @@
     "max_input_chars_per_word": 100,
     "vocab": {
       "[PAD]": 0,
-      "[unused0]": 1,
       "[unused1]": 2,
       "[unused2]": 3,
       "[unused3]": 4,

   "pre_tokenizer": {
     "type": "BertPreTokenizer"
   },
   "decoder": {
     "type": "WordPiece",
     "prefix": "##",
     "max_input_chars_per_word": 100,
     "vocab": {
       "[PAD]": 0,
+      "[EOS]": 1,
       "[unused1]": 2,
       "[unused2]": 3,
       "[unused3]": 4,