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

Libraries

How to use tahaman/DamageCarModel with Transformers:

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

pipe = pipeline("image-text-to-text", model="tahaman/DamageCarModel", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tahaman/DamageCarModel", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("tahaman/DamageCarModel", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tahaman/DamageCarModel with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tahaman/DamageCarModel

SGLang

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

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

tahaman commited on Jul 1, 2024

Commit

dc85477

verified ·

1 Parent(s): cb25355

Upload Florence2ForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +6 -6
generation_config.json +3 -3
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,18 +1,18 @@
 {
-  "_name_or_path": "microsoft/Florence-2-base-ft",
   "architectures": [
     "Florence2ForConditionalGeneration"
   ],
   "auto_map": {
-    "AutoConfig": "microsoft/Florence-2-base-ft--configuration_florence2.Florence2Config",
-    "AutoModelForCausalLM": "microsoft/Florence-2-base-ft--modeling_florence2.Florence2ForConditionalGeneration"
   },
-  "bos_token_id": 2,
-  "eos_token_id": 1,
   "ignore_index": -100,
   "is_encoder_decoder": true,
   "model_type": "florence2",
-  "pad_token_id": 0,
   "projection_dim": 768,
   "text_config": {
     "_name_or_path": "",

 {
+  "_name_or_path": "microsoft/Florence-2-base",
   "architectures": [
     "Florence2ForConditionalGeneration"
   ],
   "auto_map": {
+    "AutoConfig": "microsoft/Florence-2-base--configuration_florence2.Florence2Config",
+    "AutoModelForCausalLM": "microsoft/Florence-2-base--modeling_florence2.Florence2ForConditionalGeneration"
   },
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "ignore_index": -100,
   "is_encoder_decoder": true,
   "model_type": "florence2",
+  "pad_token_id": 1,
   "projection_dim": 768,
   "text_config": {
     "_name_or_path": "",

generation_config.json CHANGED Viewed

@@ -1,13 +1,13 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
   "decoder_start_token_id": 2,
   "early_stopping": true,
-  "eos_token_id": 1,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "no_repeat_ngram_size": 3,
   "num_beams": 3,
-  "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,
+  "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "no_repeat_ngram_size": 3,
   "num_beams": 3,
+  "pad_token_id": 1,
   "transformers_version": "4.41.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f8cad8a47cfb546c414958860c2b1a1251306107472eb7921c4b80b7fb75e5
 size 1083916964

 version https://git-lfs.github.com/spec/v1
+oid sha256:dc0536d2d3106b0c3a9c4d9c4618b6778ab2f4c34a86c7459522c63652e17064
 size 1083916964