Instructions to use Shadowmachete/vlm_captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shadowmachete/vlm_captioning with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Shadowmachete/vlm_captioning")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Shadowmachete/vlm_captioning") model = AutoModelForImageTextToText.from_pretrained("Shadowmachete/vlm_captioning") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Shadowmachete/vlm_captioning with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Shadowmachete/vlm_captioning" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Shadowmachete/vlm_captioning", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Shadowmachete/vlm_captioning
- SGLang
How to use Shadowmachete/vlm_captioning 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 "Shadowmachete/vlm_captioning" \ --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": "Shadowmachete/vlm_captioning", "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 "Shadowmachete/vlm_captioning" \ --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": "Shadowmachete/vlm_captioning", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Shadowmachete/vlm_captioning with Docker Model Runner:
docker model run hf.co/Shadowmachete/vlm_captioning
Training in progress, epoch 1
Browse files- config.json +34 -0
- model.safetensors +3 -0
- runs/May15_22-21-50_LAPTOP-RETT3JD7/events.out.tfevents.1715782952.LAPTOP-RETT3JD7.7284.0 +3 -0
- runs/May15_22-21-50_LAPTOP-RETT3JD7/events.out.tfevents.1715782977.LAPTOP-RETT3JD7.7284.1 +3 -0
- runs/May16_07-11-59_LAPTOP-RETT3JD7/events.out.tfevents.1715814725.LAPTOP-RETT3JD7.18836.0 +3 -0
- runs/May16_07-33-12_LAPTOP-RETT3JD7/events.out.tfevents.1715815995.LAPTOP-RETT3JD7.18836.1 +3 -0
- runs/May16_07-43-43_LAPTOP-RETT3JD7/events.out.tfevents.1715816629.LAPTOP-RETT3JD7.17056.0 +3 -0
- runs/May16_07-46-21_LAPTOP-RETT3JD7/events.out.tfevents.1715816793.LAPTOP-RETT3JD7.17056.1 +3 -0
- runs/May16_07-48-26_LAPTOP-RETT3JD7/events.out.tfevents.1715816909.LAPTOP-RETT3JD7.16920.0 +3 -0
- runs/May16_07-58-20_LAPTOP-RETT3JD7/events.out.tfevents.1715817507.LAPTOP-RETT3JD7.16280.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/git-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GitForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 101,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 102,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 1024,
|
| 17 |
+
"model_type": "git",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"num_image_with_embedding": null,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.40.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vision_config": {
|
| 28 |
+
"dropout": 0.0,
|
| 29 |
+
"initializer_factor": 1.0,
|
| 30 |
+
"model_type": "git_vision_model",
|
| 31 |
+
"projection_dim": 512
|
| 32 |
+
},
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd5a9ad6b9fbb3a03b52caaa2fc54f6dbc95269caa7dfa309933938d8017e7c4
|
| 3 |
+
size 706516040
|
runs/May15_22-21-50_LAPTOP-RETT3JD7/events.out.tfevents.1715782952.LAPTOP-RETT3JD7.7284.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:251e1c82f8bb0e88db8fd0d29be5fe709db864db40f6f3e9183eda75bcdabe53
|
| 3 |
+
size 4896
|
runs/May15_22-21-50_LAPTOP-RETT3JD7/events.out.tfevents.1715782977.LAPTOP-RETT3JD7.7284.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1294c1723c601f958e283ff825ed00adca013aedb0f7d53d1358d7b09f730149
|
| 3 |
+
size 4896
|
runs/May16_07-11-59_LAPTOP-RETT3JD7/events.out.tfevents.1715814725.LAPTOP-RETT3JD7.18836.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2aba558e06bd40675fd25140a440f6a22a64fb0e1335a031f2df7a7b650ab2d
|
| 3 |
+
size 4896
|
runs/May16_07-33-12_LAPTOP-RETT3JD7/events.out.tfevents.1715815995.LAPTOP-RETT3JD7.18836.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33d43c832f9412d591ca3939ed1a627ec3ac629603b233190857aee3590bfe00
|
| 3 |
+
size 4896
|
runs/May16_07-43-43_LAPTOP-RETT3JD7/events.out.tfevents.1715816629.LAPTOP-RETT3JD7.17056.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a1f0405a976d1f4d4cb48138db91d0b9fb718bba04c02cd04a9efa4ca67a5aa
|
| 3 |
+
size 4896
|
runs/May16_07-46-21_LAPTOP-RETT3JD7/events.out.tfevents.1715816793.LAPTOP-RETT3JD7.17056.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d389a2b58f418956875d37493f607c583f72abf545738b6ed0b38e5f60d281c6
|
| 3 |
+
size 4896
|
runs/May16_07-48-26_LAPTOP-RETT3JD7/events.out.tfevents.1715816909.LAPTOP-RETT3JD7.16920.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b12f6ea9451cd3be289bf3ec2953087ac4ec43a1d25e8afa35822ff8bbbe155
|
| 3 |
+
size 4896
|
runs/May16_07-58-20_LAPTOP-RETT3JD7/events.out.tfevents.1715817507.LAPTOP-RETT3JD7.16280.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e5cdfcf313fb30f38a61de6065aae737f855a62f45cd1f2ba9d4974c184aa1
|
| 3 |
+
size 5212
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e3f88ecd1f5c6507c0be34f1c9cf4ac719f1779efc73a5c0ee5e4dc13467b6e
|
| 3 |
+
size 4984
|