Instructions to use Xenova/really-tiny-falcon-testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xenova/really-tiny-falcon-testing with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'Xenova/really-tiny-falcon-testing');

Transformers

How to use Xenova/really-tiny-falcon-testing with Transformers:

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

pipe = pipeline("text-generation", model="Xenova/really-tiny-falcon-testing", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xenova/really-tiny-falcon-testing", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Xenova/really-tiny-falcon-testing", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Xenova/really-tiny-falcon-testing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Xenova/really-tiny-falcon-testing

SGLang

How to use Xenova/really-tiny-falcon-testing 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 "Xenova/really-tiny-falcon-testing" \
    --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": "Xenova/really-tiny-falcon-testing",
		"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 "Xenova/really-tiny-falcon-testing" \
        --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": "Xenova/really-tiny-falcon-testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xenova/really-tiny-falcon-testing with Docker Model Runner:
```
docker model run hf.co/Xenova/really-tiny-falcon-testing
```

Xenova HF Staff commited on Nov 3, 2023

Commit

20a7971

1 Parent(s): 058e9cd

Update config.json

Browse files

Files changed (1) hide show

config.json +6 -10

config.json CHANGED Viewed

@@ -7,12 +7,12 @@
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
-    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -25,13 +25,9 @@
   "model_type": "falcon",
   "multi_query": true,
   "new_decoder_architecture": false,
-  "nm_kv_hears": 2,
   "num_attention_heads": 2,
   "num_hidden_layers": 2,
-  "num_kv_heads": 71,
   "parallel_attn": true,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 65024

   ],
   "attention_dropout": 0.0,
   "auto_map": {
+    "AutoConfig": "configuration_falcon.FalconConfig",
+    "AutoModel": "modeling_falcon.FalconModel",
+    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
+    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
   },
   "bias": false,
   "bos_token_id": 11,
   "model_type": "falcon",
   "multi_query": true,
   "new_decoder_architecture": false,
   "num_attention_heads": 2,
   "num_hidden_layers": 2,
   "parallel_attn": true,
   "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 65024