Model reference · open weights
v-gpt2-image-captioning is an open-weight language model from nlpconnect, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
nlpconnect/vit-gpt2-image-captioning This is an image captioning model trained by @ydshieh in flax this is pytorch version of this. The Illustrated Image Captioning using transformers https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/ Sample running code Sample running code using transformers pipeline Contact for any help https://huggingface.co/ankur310794 https://twitter.com/ankur310794 http://github.com/ankur3107 https://www.linkedin.com/in/ankur310794
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nlpconnect |
|---|---|
| Type | Language models |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 103k downloads / month |
| Likes | 934 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| vit-gpt2-image-captioning | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys v-gpt2-image-captioning for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (v-gpt2-image-captioning below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"v-gpt2-image-captioning","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗