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

Libraries

How to use siddanshchawla/adapter_test with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("siddanshchawla/adapter_test")
model = AutoModelForCausalLM.from_pretrained("siddanshchawla/adapter_test", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use siddanshchawla/adapter_test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/siddanshchawla/adapter_test

SGLang

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

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

siddanshchawla commited on Mar 21, 2024

Commit

e8439ec

verified ·

1 Parent(s): 8257a79

Delete trainer_state.json

Browse files

Files changed (1) hide show

trainer_state.json +0 -36

trainer_state.json DELETED Viewed

@@ -1,36 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 63,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.79,
-      "grad_norm": 1.3655260801315308,
-      "learning_rate": 9.059690028579284e-05,
-      "loss": 2.2708,
-      "step": 50
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 1.9815729856491089,
-      "eval_runtime": 13.5787,
-      "eval_samples_per_second": 7.364,
-      "eval_steps_per_second": 0.957,
-      "step": 63
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 252,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 500,
-  "total_flos": 8710557850927104.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}