GLM-4.6
Collection
5 items
•
Updated
•
21
Alexey Dertev
d8rt8v
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
5 days ago
GLM-4.6
liked
a model
23 days ago
google/embeddinggemma-300m
reacted
to
prithivMLmods's
post
with ❤️
26 days ago
Introducing Gliese-OCR-7B-Post1.0, a document content-structure retrieval VLM designed for content extraction(OCRs) and summarization. This is the third model in the Camel Doc OCR VLM series, following Camel-Doc-OCR-062825. The new version fixes formal table reconstruction issues in both En and Zh, achieving optimal performance for long-context inferences. This model also shows significant improvements in LaTeX and Markdown rendering for OCR tasks.
🤗 Gliese-OCR-7B-Post1.0 : https://huggingface.co/prithivMLmods/Gliese-OCR-7B-Post1.0
📌 Gliese-Post1.0 Collection : https://huggingface.co/collections/prithivMLmods/gliese-post10-68c52c4a6ca4935f5259a6d7
⬅️ Previous Versions : https://huggingface.co/prithivMLmods/Camel-Doc-OCR-062825
🧨 Gliese-OCR-7B-Post1.0 (4-bit) Notebook Demo on T4 : https://huggingface.co/prithivMLmods/Gliese-OCR-7B-Post1.0/blob/main/Gliese-OCR-7B-Post1.0(4-bit)-reportlab/Gliese_OCR_7B_Post1_0(4_bit)_reportlab.ipynb
📖 GitHub [Gliese-OCR-7B-Post1.0(4-bit)-reportlab] : https://tinyurl.com/ys7zuerc
Other Collections:
➔ Multimodal Implementations : https://huggingface.co/collections/prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
➔ Multimodal VLMs - Aug'25 : https://huggingface.co/collections/prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
➔ Multimodal VLMs - July'25 : https://huggingface.co/collections/prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
.
.
.
To know more about it, visit the app page or the respective model page!!
Organizations
None yet
upvoted
a
collection
5 days ago
liked
a
model
23 days ago
reacted to
prithivMLmods's
post with ❤️
26 days ago
Post
7169
Introducing Gliese-OCR-7B-Post1.0, a document content-structure retrieval VLM designed for content extraction(OCRs) and summarization. This is the third model in the Camel Doc OCR VLM series, following Camel-Doc-OCR-062825. The new version fixes formal table reconstruction issues in both En and Zh, achieving optimal performance for long-context inferences. This model also shows significant improvements in LaTeX and Markdown rendering for OCR tasks.
🤗 Gliese-OCR-7B-Post1.0 : prithivMLmods/Gliese-OCR-7B-Post1.0
📌 Gliese-Post1.0 Collection : prithivMLmods/gliese-post10-68c52c4a6ca4935f5259a6d7
⬅️ Previous Versions : prithivMLmods/Camel-Doc-OCR-062825
🧨 Gliese-OCR-7B-Post1.0 (4-bit) Notebook Demo on T4 : prithivMLmods/Gliese-OCR-7B-Post1.0
📖 GitHub [Gliese-OCR-7B-Post1.0(4-bit)-reportlab] : https://tinyurl.com/ys7zuerc
Other Collections:
➔ Multimodal Implementations : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
➔ Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
➔ Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
.
.
.
To know more about it, visit the app page or the respective model page!!
🤗 Gliese-OCR-7B-Post1.0 : prithivMLmods/Gliese-OCR-7B-Post1.0
📌 Gliese-Post1.0 Collection : prithivMLmods/gliese-post10-68c52c4a6ca4935f5259a6d7
⬅️ Previous Versions : prithivMLmods/Camel-Doc-OCR-062825
🧨 Gliese-OCR-7B-Post1.0 (4-bit) Notebook Demo on T4 : prithivMLmods/Gliese-OCR-7B-Post1.0
📖 GitHub [Gliese-OCR-7B-Post1.0(4-bit)-reportlab] : https://tinyurl.com/ys7zuerc
Other Collections:
➔ Multimodal Implementations : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
➔ Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
➔ Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
.
.
.
To know more about it, visit the app page or the respective model page!!
- 2 replies
Error when running in VLLM
👍
2
18
#1 opened 29 days ago
by
d8rt8v
liked
a
model
29 days ago
liked
2
models
about 2 months ago
liked
a
Space
6 months ago
liked
2
models
6 months ago
reacted to
onekq's
post with 😎
6 months ago
Post
2589
We desperately need GPU for model inference. CPU can't replace GPU.
I will start with the basics. GPU is designed to serve predictable workloads with many parallel units (pixels, tensors, tokens). So a GPU allocates as much transistor budget as possible to build thousands of compute units (Cuda cores in NVidia or execution units in Apple Silicon), each capable of running a thread.
But CPU is designed to handle all kinds of workloads. CPU cores are much larger (hence a lot fewer) with branch prediction and other complex things. In addition, more and more transistors are allocated to build larger cache (~50% now) to house the unpredictable, devouring the compute budget.
Generalists can't beat specialists.
I will start with the basics. GPU is designed to serve predictable workloads with many parallel units (pixels, tensors, tokens). So a GPU allocates as much transistor budget as possible to build thousands of compute units (Cuda cores in NVidia or execution units in Apple Silicon), each capable of running a thread.
But CPU is designed to handle all kinds of workloads. CPU cores are much larger (hence a lot fewer) with branch prediction and other complex things. In addition, more and more transistors are allocated to build larger cache (~50% now) to house the unpredictable, devouring the compute budget.
Generalists can't beat specialists.
- 4 replies
liked
a
model
6 months ago
upvoted
a
paper
6 months ago
liked
a
Space
6 months ago
liked
a
model
7 months ago
liked
a
Space
7 months ago
liked
a
model
7 months ago
liked
a
Space
7 months ago
liked
a
model
7 months ago
updated
a
Space
8 months ago