Instructions to use HiTruong/Sailor_chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HiTruong/Sailor_chatbot with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HiTruong/Sailor_chatbot")
model = AutoModelForCausalLM.from_pretrained("HiTruong/Sailor_chatbot")
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 Settings

vLLM

How to use HiTruong/Sailor_chatbot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HiTruong/Sailor_chatbot

SGLang

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

Docker Model Runner
How to use HiTruong/Sailor_chatbot with Docker Model Runner:
```
docker model run hf.co/HiTruong/Sailor_chatbot
```

HiTruong commited on Jul 22, 2024

Commit

efc6990

verified ·

1 Parent(s): aea23fa

Training in progress, step 4, checkpoint

Browse files

Files changed (5) hide show

last-checkpoint/adapter_config.json +3 -3
last-checkpoint/adapter_model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/trainer_state.json +3 -3
last-checkpoint/training_args.bin +1 -1

last-checkpoint/adapter_config.json CHANGED Viewed

@@ -24,12 +24,12 @@
   "revision": "unsloth",
   "target_modules": [
     "o_proj",
     "k_proj",
     "gate_proj",
-    "up_proj",
     "v_proj",
-    "q_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "revision": "unsloth",
   "target_modules": [
     "o_proj",
+    "q_proj",
     "k_proj",
+    "down_proj",
     "gate_proj",
     "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3581ef7b113a084bbc9f9dd2ffe874834774adefa434052c9b5fb9d87cafdac
 size 2969089584

 version https://git-lfs.github.com/spec/v1
+oid sha256:da1c040e73627d172bada7ede0d50219b1359e1826e0317544486ae4922aad81
 size 2969089584

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce51e357e512a178c7402e6eb912b3a13b20a74e4d296a936434945a4a5e9ed2
 size 1487821148

 version https://git-lfs.github.com/spec/v1
+oid sha256:d36ac8dc3950d91c6a4a8d4f4ea456167c4431dcee6d7510d483b3e8169a9d7f
 size 1487821148

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -8,10 +8,10 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [],
-  "logging_steps": 5,
-  "max_steps": 51,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
   "save_steps": 4,
   "stateful_callbacks": {
     "TrainerControl": {

   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [],
+  "logging_steps": 51,
+  "max_steps": 510,
   "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
   "save_steps": 4,
   "stateful_callbacks": {
     "TrainerControl": {

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d46a32d71caf88b9515c98e3a63ecadfd5151c696ec5620ec148a9806718cc8
 size 5112

 version https://git-lfs.github.com/spec/v1
+oid sha256:51ec2f7c32ed68f93a2d58b9d808c7d6e793972fdc0fe162bed80ce09ef2fc3c
 size 5112