Instructions to use shenzhi-wang/Llama3-70B-Chinese-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shenzhi-wang/Llama3-70B-Chinese-Chat with Transformers:

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

pipe = pipeline("text-generation", model="shenzhi-wang/Llama3-70B-Chinese-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shenzhi-wang/Llama3-70B-Chinese-Chat")
model = AutoModelForCausalLM.from_pretrained("shenzhi-wang/Llama3-70B-Chinese-Chat", device_map="auto")
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 shenzhi-wang/Llama3-70B-Chinese-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shenzhi-wang/Llama3-70B-Chinese-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shenzhi-wang/Llama3-70B-Chinese-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shenzhi-wang/Llama3-70B-Chinese-Chat

SGLang

How to use shenzhi-wang/Llama3-70B-Chinese-Chat 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 "shenzhi-wang/Llama3-70B-Chinese-Chat" \
    --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": "shenzhi-wang/Llama3-70B-Chinese-Chat",
		"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 "shenzhi-wang/Llama3-70B-Chinese-Chat" \
        --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": "shenzhi-wang/Llama3-70B-Chinese-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shenzhi-wang/Llama3-70B-Chinese-Chat with Docker Model Runner:
```
docker model run hf.co/shenzhi-wang/Llama3-70B-Chinese-Chat
```

Update config.json

by hiyouga - opened May 10, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-19

Files changed (3) hide show

config.json +2 -3
generation_config.json +2 -1
special_tokens_map.json +3 -15

config.json CHANGED Viewed

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,
@@ -23,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
-  "use_cache": false,
   "vocab_size": 128256
 }

 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
+  "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
   "transformers_version": "4.40.0"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "pad_token_id": 128009,
   "transformers_version": "4.40.0"
 }

special_tokens_map.json CHANGED Viewed

@@ -1,17 +1,5 @@
 {
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": "<|eot_id|>"
-}

 {
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
   "pad_token": "<|eot_id|>"
+}