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

Libraries

How to use BEGADE/chat with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEGADE/chat")
model = AutoModelForCausalLM.from_pretrained("BEGADE/chat")
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

vLLM

How to use BEGADE/chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BEGADE/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": "BEGADE/chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BEGADE/chat

SGLang

How to use BEGADE/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 "BEGADE/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": "BEGADE/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 "BEGADE/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": "BEGADE/chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

BEGADE commited on Oct 15, 2024

Commit

14085e4

verified ·

1 Parent(s): 28a4327

Model save

Browse files

Files changed (1) hide show

README.md +12 -11

README.md CHANGED Viewed

@@ -1,13 +1,13 @@
 ---
-library_name: transformers
-license: mit
-base_model: openai-community/gpt2
 tags:
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- generator
 model-index:
 - name: chat
   results: []
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 # chat
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the generator dataset.
 ## Model description
@@ -38,15 +38,15 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 6
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 5
 ### Training results
@@ -54,7 +54,8 @@ The following hyperparameters were used during training:
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.19.1

 ---
+base_model: google/gemma-2-2b-it
+datasets:
+- generator
+library_name: peft
+license: gemma
 tags:
 - trl
 - sft
 - generated_from_trainer
 model-index:
 - name: chat
   results: []
 # chat
+This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the generator dataset.
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2
 ### Training results
 ### Framework versions
+- PEFT 0.13.2
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
+- Tokenizers 0.19.1