text-generation-inference/server/text_generation_server/models/custom_modeling/vlm.py

70 lines
2.6 KiB
Python
Raw Normal View History

Idefics2. (#1756) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-04-23 21:04:44 +00:00
def load_text_model(prefix, config, weights, name=None):
if config.model_type == "llama":
from text_generation_server.models.custom_modeling.flash_llama_modeling import (
FlashLlamaForCausalLM,
)
return FlashLlamaForCausalLM(prefix, config, weights, name=name)
Idefics2. (#1756) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-04-23 21:04:44 +00:00
elif config.model_type == "mistral":
from text_generation_server.models.custom_modeling.flash_mistral_modeling import (
FlashMistralForCausalLM,
)
return FlashMistralForCausalLM(prefix, config, weights, name=name)
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-16 04:58:47 +00:00
elif config.model_type == "gemma":
from text_generation_server.models.custom_modeling.flash_gemma_modeling import (
FlashGemmaForCausalLM,
)
return FlashGemmaForCausalLM(prefix, config, weights, causal=False)
elif config.model_type == "gemma2":
from text_generation_server.models.custom_modeling.flash_gemma2_modeling import (
FlashGemma2ForCausalLM,
)
return FlashGemma2ForCausalLM(prefix, config, weights)
2025-03-12 08:25:51 +00:00
elif config.model_type == "gemma3" or config.model_type == "gemma3_text":
from text_generation_server.models.custom_modeling.flash_gemma3_modeling import (
FlashGemma3ForCausalLM,
)
return FlashGemma3ForCausalLM(prefix, config, weights)
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-16 04:58:47 +00:00
elif config.model_type == "paligemma":
from text_generation_server.models.custom_modeling.flash_gemma_modeling import (
FlashGemmaForCausalLM,
)
return FlashGemmaForCausalLM(prefix, config, weights)
Idefics2. (#1756) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-04-23 21:04:44 +00:00
else:
raise RuntimeError(f"Unsupported model type {config.model_type}")
def load_vision_model(prefix, config, weights):
if config.model_type == "clip_vision_model":
from text_generation_server.models.custom_modeling.clip import (
CLIPVisionTransformer,
)
return CLIPVisionTransformer(
prefix=f"{prefix}.vision_model", config=config, weights=weights
)
2025-03-12 08:25:51 +00:00
if (
config.model_type == "siglip_vision_model"
or config.model_type == "gemma3_vision"
):
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-16 04:58:47 +00:00
from text_generation_server.models.custom_modeling.siglip import (
SiglipVisionTransformer,
)
2025-03-12 08:25:51 +00:00
# TODO: ensure that using the prefix doesn't break any existing models
# that rely on the old prefix (update the old models if necessary)
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-16 04:58:47 +00:00
return SiglipVisionTransformer(
2025-03-12 08:25:51 +00:00
# prefix="vision_model.vision_model", config=config, weights=weights
prefix=f"{prefix}.vision_model",
config=config,
weights=weights,
Pali gemma modeling (#1895) This PR adds paligemma modeling code Blog post: https://huggingface.co/blog/paligemma Transformers PR: https://github.com/huggingface/transformers/pull/30814 install the latest changes and run with ```bash # get the weights # text-generation-server download-weights gv-hf/PaliGemma-base-224px-hf # run TGI text-generation-launcher --model-id gv-hf/PaliGemma-base-224px-hf ``` basic example sending various requests ```python from huggingface_hub import InferenceClient client = InferenceClient("http://127.0.0.1:3000") images = [ "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/cow_beach_1.png", "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png", ] prompts = [ "What animal is in this image?", "Name three colors in this image.", "What are 10 colors in this image?", "Where is the cow standing?", "answer en Where is the cow standing?", "Is there a bird in the image?", "Is ther a cow in the image?", "Is there a rabbit in the image?", "how many birds are in the image?", "how many rabbits are in the image?", ] for img in images: print(f"\nImage: {img.split('/')[-1]}") for prompt in prompts: inputs = f"![]({img}){prompt}\n" json_data = { "inputs": inputs, "parameters": { "max_new_tokens": 30, "do_sample": False, }, } generated_output = client.text_generation(prompt, max_new_tokens=30, stream=False) print([f"{prompt}\n{generated_output}"]) ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-05-16 04:58:47 +00:00
)
Idefics2. (#1756) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-04-23 21:04:44 +00:00
else:
raise RuntimeError(f"Unsupported model type {config.model_type}")