Instructions to use baichuan-inc/Baichuan-13B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baichuan-inc/Baichuan-13B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="baichuan-inc/Baichuan-13B-Chat", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use baichuan-inc/Baichuan-13B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "baichuan-inc/Baichuan-13B-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baichuan-inc/Baichuan-13B-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/baichuan-inc/Baichuan-13B-Chat

SGLang

How to use baichuan-inc/Baichuan-13B-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 "baichuan-inc/Baichuan-13B-Chat" \
    --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": "baichuan-inc/Baichuan-13B-Chat",
		"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 "baichuan-inc/Baichuan-13B-Chat" \
        --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": "baichuan-inc/Baichuan-13B-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use baichuan-inc/Baichuan-13B-Chat with Docker Model Runner:
```
docker model run hf.co/baichuan-inc/Baichuan-13B-Chat
```

GuoPD commited on Aug 1, 2023

Commit

dcbaaf5

1 Parent(s): b3ca596

modify: update 13B chat model

Browse files

Files changed (5) hide show

generation_config.json +2 -1
modeling_baichuan.py +1 -3
pytorch_model-00001-of-00003.bin +2 -2
pytorch_model-00002-of-00003.bin +2 -2
pytorch_model-00003-of-00003.bin +2 -2

generation_config.json CHANGED Viewed

@@ -10,5 +10,6 @@
   "top_p": 0.85,
   "repetition_penalty": 1.1,
   "do_sample": true,
-  "transformers_version": "4.29.2"
 }

   "top_p": 0.85,
   "repetition_penalty": 1.1,
   "do_sample": true,
+  "transformers_version": "4.29.2",
+  "no_add_eos": true
 }

modeling_baichuan.py CHANGED Viewed

@@ -572,9 +572,7 @@ class BaichuanForCausalLM(BaichuanPreTrainedModel):
             elif message['role'] == 'assistant':
                 round_input = [
                     self.generation_config.assistant_token_id
-                ] + content_tokens + [
-                    self.generation_config.eos_token_id
-                ] + round_input
             else:
                 raise ValueError(f"message role not supported yet: {message['role']}")
         total_input = total_input[-max_input_tokens:]  # truncate left

             elif message['role'] == 'assistant':
                 round_input = [
                     self.generation_config.assistant_token_id
+                ] + content_tokens + round_input
             else:
                 raise ValueError(f"message role not supported yet: {message['role']}")
         total_input = total_input[-max_input_tokens:]  # truncate left

pytorch_model-00001-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc177b37a53447a91c165c0ba53629e5e4eb74ff7c3981185aca18e9556ba59e
-size 9972281188

 version https://git-lfs.github.com/spec/v1
+oid sha256:493368dd0c14f9e93a9359dcdbbe1640a70c5691851d502867e46df5e3e72e50
+size 9972279780

pytorch_model-00002-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab48918420e7f7bc965c919e53c57041909a99b430b5472589d6418cc13ee77
-size 9947421360

 version https://git-lfs.github.com/spec/v1
+oid sha256:83b12d88f4aa459f377dd714866fa2b81c99e88fefec727286ea302515ef4aed
+size 9947419824

pytorch_model-00003-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d07290b5739ea068dec0f816789596d7cc33c4f4e72cd700fe7cf5084ab05d9
-size 6610200289

 version https://git-lfs.github.com/spec/v1
+oid sha256:788ef65efe2ce412605cc81a056db2784235cec23cfccd1d9d3bed64b3e4d3be
+size 6610199329