Instructions to use ryanu/EEVE-summarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ryanu/EEVE-summarize with Transformers:

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

pipe = pipeline("text-generation", model="ryanu/EEVE-summarize")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ryanu/EEVE-summarize")
model = AutoModelForCausalLM.from_pretrained("ryanu/EEVE-summarize")
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 ryanu/EEVE-summarize with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ryanu/EEVE-summarize

SGLang

How to use ryanu/EEVE-summarize 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 "ryanu/EEVE-summarize" \
    --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": "ryanu/EEVE-summarize",
		"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 "ryanu/EEVE-summarize" \
        --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": "ryanu/EEVE-summarize",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ryanu/EEVE-summarize with Docker Model Runner:
```
docker model run hf.co/ryanu/EEVE-summarize
```

ryanu commited on Apr 17, 2024

Commit

9fa0195

verified ·

1 Parent(s): a3c3eb8

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +1 -1
tokenizer.json +0 -0
tokenizer_config.json +6 -6

special_tokens_map.json CHANGED Viewed

@@ -15,7 +15,7 @@
   },
   "pad_token": "<|im_end|>",
   "unk_token": {
-    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

   },
   "pad_token": "<|im_end|>",
   "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json CHANGED Viewed

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

tokenizer_config.json CHANGED Viewed

@@ -2,15 +2,15 @@
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "58940": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -18,7 +18,7 @@
       "single_word": false,
       "special": true
     },
-    "58941": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -26,7 +26,7 @@
       "single_word": false,
       "special": true
     },
-    "58943": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -47,7 +47,7 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "trust_remote_code": false,
-  "unk_token": "<|endoftext|>",
   "use_default_system_prompt": false,
   "use_fast": true
 }

   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "1": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "2": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "32000": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "trust_remote_code": false,
+  "unk_token": "<unk>",
   "use_default_system_prompt": false,
   "use_fast": true
 }