dstack to manage clusters of on-prem servers for AI workloads with ease
ā¢
7
chansung park PRO
chansung
AI & ML interests
None yet
Recent Activity
reacted
to
their
post
with š
3 days ago
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the @akhaliq )
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
posted
an
update
3 days ago
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the @akhaliq )
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
reacted
to
their
post
with š
4 days ago
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
Articles
Organizations
chansung's activity
reacted to
their
post with š
3 days ago
Post
1514
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the
@akhaliq
)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
posted
an
update
3 days ago
Post
1514
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the
@akhaliq
)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
reacted to
their
post with š
4 days ago
Post
1889
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
posted
an
update
4 days ago
Post
1889
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
reacted to
their
post with š
5 days ago
Post
1944
Simple Summarization on DeepSeek-R1 from DeepSeek AI
The RL stage is very important.
ā³ However, it is difficult to create a truly helpful AI for people solely through RL.
ā³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
ā³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
The RL stage is very important.
ā³ However, it is difficult to create a truly helpful AI for people solely through RL.
ā³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
ā³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
- 1 reply
posted
an
update
5 days ago
Post
1944
Simple Summarization on DeepSeek-R1 from DeepSeek AI
The RL stage is very important.
ā³ However, it is difficult to create a truly helpful AI for people solely through RL.
ā³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
ā³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
The RL stage is very important.
ā³ However, it is difficult to create a truly helpful AI for people solely through RL.
ā³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
ā³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
-
- 1 reply
upvoted
an
article
6 days ago
Article
Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
ā¢
60
authored
a
paper
about 1 month ago
upvoted
a
paper
about 1 month ago
commented
a
paper
about 1 month ago
updated
8
datasets
2 months ago
klcsp/summarization-eval-11-v1
Viewer
ā¢
Updated
ā¢
2.1k
ā¢
115
klcsp/coding-eval-11-v1
Viewer
ā¢
Updated
ā¢
1.54k
ā¢
118
klcsp/coding-response-11-v1
Viewer
ā¢
Updated
ā¢
1.54k
ā¢
39
klcsp/summarization-response-11-v1
Viewer
ā¢
Updated
ā¢
2k
ā¢
111
klcsp/closedqa-eval-11-v1
Viewer
ā¢
Updated
ā¢
1.14k
ā¢
259
klcsp/classification-eval-11-v1
Viewer
ā¢
Updated
ā¢
1.28k
ā¢
42
klcsp/closedqa-response-11-v1
Viewer
ā¢
Updated
ā¢
1.2k
ā¢
42
klcsp/classification-response-11-v1
Viewer
ā¢
Updated
ā¢
1.28k
ā¢
392
updated
2
models
2 months ago