Instructions to use yentinglin/Llama-3-Taiwan-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yentinglin/Llama-3-Taiwan-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="yentinglin/Llama-3-Taiwan-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yentinglin/Llama-3-Taiwan-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("yentinglin/Llama-3-Taiwan-8B-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yentinglin/Llama-3-Taiwan-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yentinglin/Llama-3-Taiwan-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yentinglin/Llama-3-Taiwan-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yentinglin/Llama-3-Taiwan-8B-Instruct

SGLang

How to use yentinglin/Llama-3-Taiwan-8B-Instruct 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 "yentinglin/Llama-3-Taiwan-8B-Instruct" \
    --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": "yentinglin/Llama-3-Taiwan-8B-Instruct",
		"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 "yentinglin/Llama-3-Taiwan-8B-Instruct" \
        --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": "yentinglin/Llama-3-Taiwan-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yentinglin/Llama-3-Taiwan-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/yentinglin/Llama-3-Taiwan-8B-Instruct
```

yentinglin

minyichen commited on Jul 1, 2024

Commit

f4b968f

verified ·

1 Parent(s): 609a0eb

Update tokenizer_config.json (#4)

Browse files

- Upload tokenizer_config.json (263d7ce5e63f267f17db7a12c4b89f14c990b67f)
- Update tokenizer_config.json (72d02df0c343329511e796e7e67b5dbbf4a191fa)
- Update special_tokens_map.json (f7f8f66ce688863cfbe19514484a2f2b82080926)

Co-authored-by: minyi <minyichen@users.noreply.huggingface.co>

Files changed (2) hide show

special_tokens_map.json +1 -1
tokenizer_config.json +2 -2

special_tokens_map.json CHANGED Viewed

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

     "single_word": false
   },
   "eos_token": {
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json CHANGED Viewed

@@ -2066,9 +2066,9 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"

     }
   },
   "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"