Instructions to use Frinkles/RiPPL-Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Frinkles/RiPPL-Alpha with Transformers:

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

pipe = pipeline("text-generation", model="Frinkles/RiPPL-Alpha", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Frinkles/RiPPL-Alpha", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Frinkles/RiPPL-Alpha", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Frinkles/RiPPL-Alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Frinkles/RiPPL-Alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frinkles/RiPPL-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Frinkles/RiPPL-Alpha

SGLang

How to use Frinkles/RiPPL-Alpha 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 "Frinkles/RiPPL-Alpha" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frinkles/RiPPL-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Frinkles/RiPPL-Alpha" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frinkles/RiPPL-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Frinkles/RiPPL-Alpha with Docker Model Runner:
```
docker model run hf.co/Frinkles/RiPPL-Alpha
```

Frinkles commited on Jul 16, 2024

Commit

0fb34c1

verified ·

1 Parent(s): 89c89ad

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +0 -0
tokenizer_config.json +11 -19

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -20,14 +20,6 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
@@ -35,7 +27,7 @@
       "single_word": false,
       "special": true
     },
-    "32001": {
       "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
@@ -43,7 +35,7 @@
       "single_word": false,
       "special": true
     },
-    "32002": {
       "content": "<|placeholder1|>",
       "lstrip": false,
       "normalized": false,
@@ -51,7 +43,7 @@
       "single_word": false,
       "special": true
     },
-    "32003": {
       "content": "<|placeholder2|>",
       "lstrip": false,
       "normalized": false,
@@ -59,7 +51,7 @@
       "single_word": false,
       "special": true
     },
-    "32004": {
       "content": "<|placeholder3|>",
       "lstrip": false,
       "normalized": false,
@@ -67,7 +59,7 @@
       "single_word": false,
       "special": true
     },
-    "32005": {
       "content": "<|placeholder4|>",
       "lstrip": false,
       "normalized": false,
@@ -75,7 +67,7 @@
       "single_word": false,
       "special": true
     },
-    "32006": {
       "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
@@ -83,7 +75,7 @@
       "single_word": false,
       "special": true
     },
-    "32007": {
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
@@ -91,7 +83,7 @@
       "single_word": false,
       "special": true
     },
-    "32008": {
       "content": "<|placeholder5|>",
       "lstrip": false,
       "normalized": false,
@@ -99,7 +91,7 @@
       "single_word": false,
       "special": true
     },
-    "32009": {
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
@@ -107,7 +99,7 @@
       "single_word": false,
       "special": true
     },
-    "32010": {
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
@@ -121,7 +113,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,
-  "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "sp_model_kwargs": {},

       "special": true
     },
     "2": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "3": {
       "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "4": {
       "content": "<|placeholder1|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "5": {
       "content": "<|placeholder2|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "6": {
       "content": "<|placeholder3|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "7": {
       "content": "<|placeholder4|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "8": {
       "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "9": {
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "10": {
       "content": "<|placeholder5|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "11": {
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "12": {
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "sp_model_kwargs": {},