Instructions to use BlackSamorez/falcon-40b-tiny-testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlackSamorez/falcon-40b-tiny-testing with Transformers:

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

pipe = pipeline("text-generation", model="BlackSamorez/falcon-40b-tiny-testing", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BlackSamorez/falcon-40b-tiny-testing", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BlackSamorez/falcon-40b-tiny-testing with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BlackSamorez/falcon-40b-tiny-testing"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BlackSamorez/falcon-40b-tiny-testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BlackSamorez/falcon-40b-tiny-testing

SGLang

How to use BlackSamorez/falcon-40b-tiny-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 "BlackSamorez/falcon-40b-tiny-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": "BlackSamorez/falcon-40b-tiny-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 "BlackSamorez/falcon-40b-tiny-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": "BlackSamorez/falcon-40b-tiny-testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BlackSamorez/falcon-40b-tiny-testing with Docker Model Runner:
```
docker model run hf.co/BlackSamorez/falcon-40b-tiny-testing
```

BlackSamorez commited on Jun 20, 2023

Commit

1b37fbd

1 Parent(s): 725e003

Upload RWForCausalLM

Browse files

Files changed (2) hide show

config.json +3 -3
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -18,12 +18,12 @@
   "bos_token_id": 11,
   "eos_token_id": 11,
   "hidden_dropout": 0.0,
-  "hidden_size": 512,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "RefinedWeb",
-  "n_head": 8,
-  "n_head_kv": 2,
   "n_layer": 2,
   "parallel_attn": true,
   "torch_dtype": "float32",

   "bos_token_id": 11,
   "eos_token_id": 11,
   "hidden_dropout": 0.0,
+  "hidden_size": 256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "RefinedWeb",
+  "n_head": 4,
+  "n_head_kv": 4,
   "n_layer": 2,
   "parallel_attn": true,
   "torch_dtype": "float32",

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15048f35c4ed3eaf650b9d132c280af1ae7b023fba16d29d5b913d98aaa195b8
-size 155215850

 version https://git-lfs.github.com/spec/v1
+oid sha256:39a9a2712511a248e04220ab9cb60aa654acc7e403257d41f5db152b19ffb667
+size 72892394