Instructions to use hf-internal-testing/tiny-random-FuyuForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-FuyuForCausalLM with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-FuyuForCausalLM")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-FuyuForCausalLM")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-FuyuForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-FuyuForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-FuyuForCausalLM

SGLang

How to use hf-internal-testing/tiny-random-FuyuForCausalLM 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 "hf-internal-testing/tiny-random-FuyuForCausalLM" \
    --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": "hf-internal-testing/tiny-random-FuyuForCausalLM",
		"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 "hf-internal-testing/tiny-random-FuyuForCausalLM" \
        --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": "hf-internal-testing/tiny-random-FuyuForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-FuyuForCausalLM with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-FuyuForCausalLM
```

Update tiny models for FuyuForCausalLM

by hf-transformers-bot - opened Nov 23, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (2) hide show

config.json +2 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -27,8 +27,6 @@
   "rope_scaling": null,
   "rope_theta": 25000.0,
   "text_config": {
-    "bos_token_id": 71013,
-    "eos_token_id": 71013,
     "hidden_act": "gelu",
     "hidden_size": 32,
     "intermediate_size": 37,
@@ -36,7 +34,8 @@
     "model_type": "persimmon",
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
-    "pad_token_id": 0
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

   "rope_scaling": null,
   "rope_theta": 25000.0,
   "text_config": {
     "hidden_act": "gelu",
     "hidden_size": 32,
     "intermediate_size": 37,
     "model_type": "persimmon",
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
+    "pad_token_id": 0,
+    "vocab_size": 99
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31af5daf3680066587dd8904ce7f6c0ac3af607e617c1b41e66488204d9a0f7f
-size 67514008

 version https://git-lfs.github.com/spec/v1
+oid sha256:caa01bcd251931627892a9728493cf115bb1022a2a7f9e493cd6e21a9618add5
+size 430256