Instructions to use euclaise/falcon_1b_stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use euclaise/falcon_1b_stage1 with Transformers:

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

pipe = pipeline("text-generation", model="euclaise/falcon_1b_stage1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("euclaise/falcon_1b_stage1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("euclaise/falcon_1b_stage1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use euclaise/falcon_1b_stage1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "euclaise/falcon_1b_stage1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "euclaise/falcon_1b_stage1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/euclaise/falcon_1b_stage1

SGLang

How to use euclaise/falcon_1b_stage1 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 "euclaise/falcon_1b_stage1" \
    --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": "euclaise/falcon_1b_stage1",
		"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 "euclaise/falcon_1b_stage1" \
        --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": "euclaise/falcon_1b_stage1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use euclaise/falcon_1b_stage1 with Docker Model Runner:
```
docker model run hf.co/euclaise/falcon_1b_stage1
```

euclaise commited on Sep 17, 2023

Commit

bdc60f3

1 Parent(s): 282db55

End of training

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0869
 ## Model description
@@ -42,14 +42,14 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128.0
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.0952        | 1.0   | 658  | 2.0869          |
 ### Framework versions

 This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.0640
 ## Model description
 - total_train_batch_size: 128.0
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.2
 - num_epochs: 1
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 2.0522        | 1.0   | 652  | 2.0640          |
 ### Framework versions