Instructions to use haidlir/bloom-chatml-id with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haidlir/bloom-chatml-id with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("haidlir/bloom-chatml-id")
model = AutoModelForCausalLM.from_pretrained("haidlir/bloom-chatml-id")
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 haidlir/bloom-chatml-id with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/haidlir/bloom-chatml-id

SGLang

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

Docker Model Runner
How to use haidlir/bloom-chatml-id with Docker Model Runner:
```
docker model run hf.co/haidlir/bloom-chatml-id
```

Update README.md

by haidlir - opened Jan 16, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+14

-6

Files changed (1) hide show

README.md +14 -6

README.md CHANGED Viewed

@@ -20,11 +20,19 @@ pipeline_tag: text-generation
 - https://huggingface.co/datasets/jakartaresearch/indoqa
-**Task**: Chat or Conversational
-**Input**: User's prompt containing chat templated text in string format
-**Output**: Model's generated text in string format
 **Experiment**:
-- Use bos and eos token to replace <|im_start|> and <|im_end|> in ChatML. (Inspired by: https://asmirnov.xyz/doppelganger)
-- Penggunaan padding dan truncation sesuai max_length.
-- Max length = 256, karena telah mengkonsumsi 33.7 GB.

 - https://huggingface.co/datasets/jakartaresearch/indoqa
+**Task**:
+Chat or Conversational
+**Input**:
+User's prompt containing chat templated text in string format
+**Output**:
+Model's generated text in string format
 **Experiment**:
+- Use bos_token and eos_token to replace <|im_start|> and <|im_end|> in ChatML. (Inspired by: https://asmirnov.xyz/doppelganger)
+- Use left padding and left truncation to conform to max_length.
+- Set max_length = 256 in the training process, which consumes 33.7 GB of memory.
+**Notebook**:
+- https://drive.google.com/file/d/11FiaWxGt2HxUirZrHTNLaVmiqrUwejwV/view?usp=drive_link