Instructions to use hugohrban/progen2-small-mix7-bidi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hugohrban/progen2-small-mix7-bidi with Transformers:

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

pipe = pipeline("text-generation", model="hugohrban/progen2-small-mix7-bidi", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hugohrban/progen2-small-mix7-bidi", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hugohrban/progen2-small-mix7-bidi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hugohrban/progen2-small-mix7-bidi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hugohrban/progen2-small-mix7-bidi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hugohrban/progen2-small-mix7-bidi

SGLang

How to use hugohrban/progen2-small-mix7-bidi 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 "hugohrban/progen2-small-mix7-bidi" \
    --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": "hugohrban/progen2-small-mix7-bidi",
		"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 "hugohrban/progen2-small-mix7-bidi" \
        --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": "hugohrban/progen2-small-mix7-bidi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hugohrban/progen2-small-mix7-bidi with Docker Model Runner:
```
docker model run hf.co/hugohrban/progen2-small-mix7-bidi
```

hugohrban commited on Apr 24, 2024

Commit

6c45e77

verified ·

1 Parent(s): 12e73a0

Create tokenizer.json

Browse files

Files changed (1) hide show

tokenizer.json +167 -0

tokenizer.json ADDED Viewed

	@@ -0,0 +1,167 @@

+{
+  "version": "1.0",
+  "truncation": {
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 1024
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|pad|>"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "special": true,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 1,
+      "special": true,
+      "content": "<|bos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 2,
+      "special": true,
+      "content": "<|eos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 30,
+      "special": false,
+      "content": "<|pf00002|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 31,
+      "special": false,
+      "content": "<|pf00042|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 32,
+      "special": false,
+      "content": "<|pf00125|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 33,
+      "special": false,
+      "content": "<|pf00127|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 34,
+      "special": false,
+      "content": "<|pf00257|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 35,
+      "special": false,
+      "content": "<|pf00262|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 36,
+      "special": false,
+      "content": "<|pf03668|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "<|pad|>": 0,
+      "<|bos|>": 1,
+      "<|eos|>": 2,
+      "1": 3,
+      "2": 4,
+      "A": 5,
+      "B": 6,
+      "C": 7,
+      "D": 8,
+      "E": 9,
+      "F": 10,
+      "G": 11,
+      "H": 12,
+      "I": 13,
+      "K": 14,
+      "L": 15,
+      "M": 16,
+      "N": 17,
+      "O": 18,
+      "P": 19,
+      "Q": 20,
+      "R": 21,
+      "S": 22,
+      "T": 23,
+      "U": 24,
+      "V": 25,
+      "W": 26,
+      "X": 27,
+      "Y": 28,
+      "Z": 29
+    },
+    "merges": []
+  }
+}