Post
22
Hey everyone! Just wanted to share this awesome dataset that features over 1 million tokens specifically for the Egyptian dialect. Check it
HeshamHaroon/1milion_token_EGY_songs
Join the conversation
Join the community of Machine Learners and AI enthusiasts.
Sign UpAll HF Hub posts
HeshamHaroon
posted an update
11 minutes ago
Hey everyone! Just wanted to share this awesome dataset that features over 1 million tokens specifically for the Egyptian dialect. Check it
HeshamHaroon/1milion_token_EGY_songs
Post
36
IBM has launched its latest #Granite code models.
𝗚𝗿𝗮𝗻𝗶𝘁𝗲 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲 - https://lnkd.in/g2KaHWxC
The figure illustrates how#Granite-8B-Code-Base outperforms #Mistral-7B, #LLama-3-8B, and other open-source models in coding tasks.
Models available:
- ibm-granite/granite-3b-code-base
- ibm-granite/granite-3b-code-instruct
- ibm-granite/granite-8b-code-base
- ibm-granite/granite-8b-code-instruct
- ibm-granite/granite-20b-code-base
- ibm-granite/granite-20b-code-instruct
- ibm-granite/granite-34b-code-base
- ibm-granite/granite-34b-code-instruct
𝗚𝗿𝗮𝗻𝗶𝘁𝗲 𝗼𝗻 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲 - https://lnkd.in/g2KaHWxC
The figure illustrates how#Granite-8B-Code-Base outperforms #Mistral-7B, #LLama-3-8B, and other open-source models in coding tasks.
Models available:
- ibm-granite/granite-3b-code-base
- ibm-granite/granite-3b-code-instruct
- ibm-granite/granite-8b-code-base
- ibm-granite/granite-8b-code-instruct
- ibm-granite/granite-20b-code-base
- ibm-granite/granite-20b-code-instruct
- ibm-granite/granite-34b-code-base
- ibm-granite/granite-34b-code-instruct
standardAI
posted an update
16 minutes ago
Post
36
Hi
@TimothyAlexisVass
, thanks for [this great blog post](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space#the-4-channels-of-the-sdxl-latents)! Shouldn't this be like that?
https://github.com/TimothyAlexisVass/hf-colorspace-blogpost/pull/1
https://github.com/TimothyAlexisVass/hf-colorspace-blogpost/pull/1
Post
93
The Hit Wall Point in Image generation models .
Post
134
Hi folks ,
colab[https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing]
#OpenSourcing
pip-code-bandit
-- a model to act as intelligence unit in agentic workflows.
pipflow
-- a library to manage and run goal oriented agentic system.
pip-code-bandit attributes-
-- number of params ~ 1.3b [2.9 Gb GPU memory footprint]
-- sequence length ~ 16.3k [Can go higher but will show performance degradation]
-- license - apache 2.0
-- instruction following , RL tuned.
-- tasks:
complex planning(plan) of sequential function calls | a list of callables and goal
corrected plan | feedback instructions with error
function calling | doc or code and goal
code generation | plan and goal
code generation | goal
doc generation | code
code generation | doc
file parsed to json | any raw data
sql generation | schema, question, instructions and examples
#Strategy
We used a simulator to simulate environments where the model could play games to achieve goals, given a set of actions available to it. All the model could do was find the right action and config to incur a positive reward. The reward policy is around the concept of a model going to a stable state of zero net sum reward for both good and bad behaviour. In this setup, the model, which was pre-trained on code, function documentation, and similar OS datasets, was RL-tuned for reliability and instruction-following.
Do try it out and let me know how its working for you.
Thank you :)
colab[https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing]
#OpenSourcing
pip-code-bandit
-- a model to act as intelligence unit in agentic workflows.
pipflow
-- a library to manage and run goal oriented agentic system.
pip-code-bandit attributes-
-- number of params ~ 1.3b [2.9 Gb GPU memory footprint]
-- sequence length ~ 16.3k [Can go higher but will show performance degradation]
-- license - apache 2.0
-- instruction following , RL tuned.
-- tasks:
complex planning(plan) of sequential function calls | a list of callables and goal
corrected plan | feedback instructions with error
function calling | doc or code and goal
code generation | plan and goal
code generation | goal
doc generation | code
code generation | doc
file parsed to json | any raw data
sql generation | schema, question, instructions and examples
#Strategy
We used a simulator to simulate environments where the model could play games to achieve goals, given a set of actions available to it. All the model could do was find the right action and config to incur a positive reward. The reward policy is around the concept of a model going to a stable state of zero net sum reward for both good and bad behaviour. In this setup, the model, which was pre-trained on code, function documentation, and similar OS datasets, was RL-tuned for reliability and instruction-following.
Do try it out and let me know how its working for you.
Thank you :)
Post
316
What are some areas that Image generation models are currently lacking in?
- 2 replies
phenixrhyder
posted an update
about 4 hours ago
Post
432
Autumn Ai scenery
Post
455
Yi－1.5シリーズがリリースされました。
このモデルは、GPT-3.5,Llama3,Claude2の性能を越していて、プログラミングの性能はGemini超えです。
最強のオープンソースモデルです。
ぜひ使ってみましょう。
01-ai/Yi-1.5-34B-Chat
このモデルは、GPT-3.5,Llama3,Claude2の性能を越していて、プログラミングの性能はGemini超えです。
最強のオープンソースモデルです。
ぜひ使ってみましょう。
01-ai/Yi-1.5-34B-Chat
takeraparterer
posted an update
about 7 hours ago
Post
658
cool i can post now
- 2 replies
Post
783
🎉 Big reveal: 01.AI Yi-1.5 models are in town!
📜 1st Apache 2.0 release
💡 Capabilities: Enhanced coding, math, reasoning, & instruction-following
🤖 Models: 34B/9B/6B, Base & Chat
🏆 Performance: Yi-1.5-34B matches or exceeds Llama 3 70B in benchmarks
🔥 Discover the power now! 01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8
📜 1st Apache 2.0 release
💡 Capabilities: Enhanced coding, math, reasoning, & instruction-following
🤖 Models: 34B/9B/6B, Base & Chat
🏆 Performance: Yi-1.5-34B matches or exceeds Llama 3 70B in benchmarks
🔥 Discover the power now! 01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8
-
- 2 replies
