sam-audio
Collection
11 items
โข
Updated
โข
96
Emre
rashakol19
ยท
AI & ML interests
None yet
Recent Activity
new activity
8 days ago
facebook/sam-audio-large:Has anyone been able to access it?
upvoted
a
collection
8 days ago
sam-audio
Organizations
Has anyone been able to access it?
โ
๐
5
11
#1 opened 8 days ago
by
Abduraxim
upvoted
a
collection
8 days ago
reacted to
m-ric's
post with ๐ฅ
11 months ago
Post
10020
Introducing ๐ผ๐ฝ๐ฒ๐ป ๐๐ฒ๐ฒ๐ฝ-๐ฅ๐ฒ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต by Hugging Face! ๐ฅ
OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.
โฑ๏ธ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! โฑ๏ธ
โก๏ธ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...
We aimed for the best performance: are the agent's answers really rigorous?
On GAIA benchmark, Deep Research had 67% accuracy on the validation set.
โก๏ธ open Deep Research is at 55% (powered by o1), it is:
- the best pass@1 solution submitted
- the best open solution ๐ช๐ช
And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !
Read the blog post ๐ https://huggingface.co/blog/open-deep-research
OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.
โฑ๏ธ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! โฑ๏ธ
โก๏ธ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...
We aimed for the best performance: are the agent's answers really rigorous?
On GAIA benchmark, Deep Research had 67% accuracy on the validation set.
โก๏ธ open Deep Research is at 55% (powered by o1), it is:
- the best pass@1 solution submitted
- the best open solution ๐ช๐ช
And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !
Read the blog post ๐ https://huggingface.co/blog/open-deep-research
liked
a
model
about 1 year ago
liked
5
models
over 1 year ago
kyutai/mimi
Feature Extraction
โข
96.2M
โข
Updated
โข
1.48M
โข
โข
273
tencent/DepthCrafter
Depth Estimation
โข
Updated
โข
58.5k
โข
103
kyutai/moshiko-pytorch-bf16
Updated
โข
195k
โข
192
microsoft/GRIN-MoE
Text Generation
โข
42B
โข
Updated
โข
12.5k
โข
198
nvidia/Nemotron-Mini-4B-Instruct
Text Generation
โข
Updated
โข
4.9k
โข
173
reacted to
Jaward's
post with ๐
over 1 year ago
Post
5523
All You need To Know About Phi-3 (Technical Report Walkthrough)
Summary of Summaries:
Phi-3-mini
- Architecture specs: decoder-only transformer, ModelSize: 3.8 billion
parameters, LongRope [ 128K Context length ], Vocab Size [ 32064 ],
trained on 3.3 trillion tokens. at bfloat16.
- Rivals performance to larger models like Mixtral 8x7B and GPT-3.5,
capable of running locally on a smartphone.
- Utilizes high quality training dataset heavily filtered from web data and
llm-generated synthetic data.
- Can be quantized to 4-bits, occupying โ 1.8GB of memory.
- Ran natively on iPhone 14 with A16 Bionic chip with inference speed of up
to 12 tokens per second.
Phi-3-small
- Architecture specs: Also decoder-only, 7B parameters, Vocab size [ 100352 ], default context length [ 8k ], Context Length: 8K, Hidden Dimension: 4096, Number of Heads and Layers: Follows 7B class structure.
- Uses tiktoken tokenizer (for enhanced multilingual tokenization)
Phi-3-medium:
- Architecture specs: Also decoder-only, Hidden Dimension: 5120, Number of Heads: 40, Number of Layers: 40, Tokenization: Consistent with other models, Training on 4.8 trillion tokens.
Training Methodology:
- Focuses on high-quality training data deviating from standard scaling laws.
- The models undergo two-phase pre-training using a mix of web sources and synthetic data for general knowledge and logical reasoning skills.
Performance:
- Phi-3-mini achieves competitive scores on standard benchmarks like MMLU and MT-Bench, indicating strong reasoning capabilities.
- Higher variants show even better performance, suggesting effective scaling with increased model size.
Limitations:
- phi-3-mini: limited by its smaller size in tasks requiring extensive factual knowledge, primarily supports English.
- phi-3-small limited multilingual support.
Hosting LLMs locally is a big win for OSS - private, secured inferencing on the go๐
Summary of Summaries:
Phi-3-mini
- Architecture specs: decoder-only transformer, ModelSize: 3.8 billion
parameters, LongRope [ 128K Context length ], Vocab Size [ 32064 ],
trained on 3.3 trillion tokens. at bfloat16.
- Rivals performance to larger models like Mixtral 8x7B and GPT-3.5,
capable of running locally on a smartphone.
- Utilizes high quality training dataset heavily filtered from web data and
llm-generated synthetic data.
- Can be quantized to 4-bits, occupying โ 1.8GB of memory.
- Ran natively on iPhone 14 with A16 Bionic chip with inference speed of up
to 12 tokens per second.
Phi-3-small
- Architecture specs: Also decoder-only, 7B parameters, Vocab size [ 100352 ], default context length [ 8k ], Context Length: 8K, Hidden Dimension: 4096, Number of Heads and Layers: Follows 7B class structure.
- Uses tiktoken tokenizer (for enhanced multilingual tokenization)
Phi-3-medium:
- Architecture specs: Also decoder-only, Hidden Dimension: 5120, Number of Heads: 40, Number of Layers: 40, Tokenization: Consistent with other models, Training on 4.8 trillion tokens.
Training Methodology:
- Focuses on high-quality training data deviating from standard scaling laws.
- The models undergo two-phase pre-training using a mix of web sources and synthetic data for general knowledge and logical reasoning skills.
Performance:
- Phi-3-mini achieves competitive scores on standard benchmarks like MMLU and MT-Bench, indicating strong reasoning capabilities.
- Higher variants show even better performance, suggesting effective scaling with increased model size.
Limitations:
- phi-3-mini: limited by its smaller size in tasks requiring extensive factual knowledge, primarily supports English.
- phi-3-small limited multilingual support.
Hosting LLMs locally is a big win for OSS - private, secured inferencing on the go๐
- 4 replies
reacted to
HaotongQin's
post with ๐
over 1 year ago
Post
1925
We release an empirical study to showcase "How Good Are Low-bit Quantized hashtag#LLaMA3 ๐ฆ Models" with existing LLM quantization techniques!
In this study, the performance of the low-bit LLaMA3 models (especially LLaMA3-70B) is impressively notable. ๐ However, the results also exposed significant performance degradation issues faced by existing quantization techniques when dealing with LLaMA3, especially under ultra-low bit-width.
We hope this study can serve as a reference for the LLM quantization community and promote the emergence of stronger LLM quantization methods in the context of LLaMA3's release. More work is on the way...
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study (2404.14047)
https://huggingface.co/collections/LLMQ/llama3-quantization-66251258525135aeda16513c
In this study, the performance of the low-bit LLaMA3 models (especially LLaMA3-70B) is impressively notable. ๐ However, the results also exposed significant performance degradation issues faced by existing quantization techniques when dealing with LLaMA3, especially under ultra-low bit-width.
We hope this study can serve as a reference for the LLM quantization community and promote the emergence of stronger LLM quantization methods in the context of LLaMA3's release. More work is on the way...
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study (2404.14047)
https://huggingface.co/collections/LLMQ/llama3-quantization-66251258525135aeda16513c
liked
a
model
about 3 years ago
