Instructions to use oplatek/falcon-7b-instruct-multi_woz_22-t2t with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oplatek/falcon-7b-instruct-multi_woz_22-t2t with Transformers:

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

pipe = pipeline("text-generation", model="oplatek/falcon-7b-instruct-multi_woz_22-t2t", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("oplatek/falcon-7b-instruct-multi_woz_22-t2t", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oplatek/falcon-7b-instruct-multi_woz_22-t2t with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oplatek/falcon-7b-instruct-multi_woz_22-t2t"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oplatek/falcon-7b-instruct-multi_woz_22-t2t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/oplatek/falcon-7b-instruct-multi_woz_22-t2t

SGLang

How to use oplatek/falcon-7b-instruct-multi_woz_22-t2t 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 "oplatek/falcon-7b-instruct-multi_woz_22-t2t" \
    --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": "oplatek/falcon-7b-instruct-multi_woz_22-t2t",
		"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 "oplatek/falcon-7b-instruct-multi_woz_22-t2t" \
        --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": "oplatek/falcon-7b-instruct-multi_woz_22-t2t",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use oplatek/falcon-7b-instruct-multi_woz_22-t2t with Docker Model Runner:
```
docker model run hf.co/oplatek/falcon-7b-instruct-multi_woz_22-t2t
```

oplatek commited on Jun 29, 2023

Commit

8820712

1 Parent(s): 193077d

Create README.md

Browse files

Files changed (1) hide show

README.md +35 -0

README.md ADDED Viewed

	@@ -0,0 +1,35 @@

+### TRAINING LOG
+wandb: Run history:
+wandb:                      eval/loss █▆▅▄▃▃▂▂▁▁▁
+wandb:                   eval/runtime ▁▃▂▃▃▃▃█▃▄▁
+wandb:        eval/samples_per_second █▆▇▆▆▆▆▁▆▄█
+wandb:          eval/steps_per_second █▆▇▆▆▆▆▁▆▄█
+wandb:                    train/epoch ▁▁▁▂▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
+wandb:              train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
+wandb:            train/learning_rate ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+wandb:                     train/loss █▄▄▅▃▅▃▃▄▅▃▃▃▄▃▃▃▃▂▂▂▂▃▂▄▂▃▂▂▂▂▂▃▂▁▃▂▂▂▁
+wandb:               train/total_flos ▁
+wandb:               train/train_loss ▁
+wandb:            train/train_runtime ▁
+wandb: train/train_samples_per_second ▁
+wandb:   train/train_steps_per_second ▁
+wandb:
+wandb: Run summary:
+wandb:                      eval/loss 0.27314
+wandb:                   eval/runtime 129.6563
+wandb:        eval/samples_per_second 7.713
+wandb:          eval/steps_per_second 7.713
+wandb:                    train/epoch 0.53
+wandb:              train/global_step 1875
+wandb:            train/learning_rate 0.0002
+wandb:                     train/loss 0.258
+wandb:               train/total_flos 1.9547706216175334e+17
+wandb:               train/train_loss 0.30445
+wandb:            train/train_runtime 13368.3721
+wandb: train/train_samples_per_second 2.244
+wandb:   train/train_steps_per_second 0.14
+wandb:
+wandb: 🚀 View run happy-deluge-17 at: https://wandb.ai/metric/llm_finetune_multiwoz22.sh/runs/4epf9h85
+### INFERENCE LOG
+TODO