Anthracite

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

lucyknada new activity 5 days ago

anthracite-org/kalo-opus-instruct-22k-no-refusal:License

Doctor-Shotgun updated a dataset 14 days ago

anthracite-org/c2_logs_32k_llama3_qwen2_v1.3

Doctor-Shotgun published a dataset 14 days ago

anthracite-org/c2_logs_32k_llama3_qwen2_v1.3

View all activity

anthracite-org's activity

grimjim

posted an update 1 day ago

Post

1533

A recent merge has provided another interesting result on the current Open LLM leaderboard.
open-llm-leaderboard/open_llm_leaderboard

Combining an o1 reasoning merge with VAGOsolutions's Llama-3.1 SauerkrautLM 8B Instruct model resulted in a lower IFEval, but a higher result in every other benchmark. This result is currently my best Llama 3.1 8B merge result to date.
grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B
The results suggest that defects in output format and/or output parsing may be limiting benchmark performance of various o1 models.

Delta-Vector

posted an update 3 days ago

Post

529

For anyone that enjoys Magnum models, I just dropped a 12B that is the first (or second?) stepping stone into Magnum V5

Delta-Vector/rei-12b-6795505005c4a94ebdfdeb39

lucyknada

in anthracite-org/kalo-opus-instruct-22k-no-refusal 5 days ago

License

#2 opened 5 days ago by

mrfakename

Doctor-Shotgun

updated a dataset 14 days ago

anthracite-org/c2_logs_32k_llama3_qwen2_v1.3

Viewer • Updated 14 days ago • 11k • 51 • 1

Doctor-Shotgun

published a dataset 14 days ago

anthracite-org/c2_logs_32k_llama3_qwen2_v1.3

Viewer • Updated 14 days ago • 11k • 51 • 1

lucyknada

in anthracite-org/magnum-v4-27b-gguf 15 days ago

Weird gibberish when using suggested template

#3 opened 15 days ago by

mrjackspade

Nitral-AI

posted an update 21 days ago

Post

3862

That moment when you spend 5 days up babysitting trains, only for colab pro + to randomly disconnect the environment at every chance with 0 error indication of any kind (it just disconnects without an error). Nuke the session from the interface, but continue to eat my colab credits while it reports to wandb. 0 way of saving the models when this happens since it nukes the code preset up to auto-execute. And since the sessions 'exist' but also at the same time doesn't exist i cant close it. And have to wait till they auto timeout after 24hrs. Guess, i won't be using colab for 'quick' test trains anymore. Thanks google for scheming the very little model training budget i had for the month.

3 replies

grimjim

posted an update 23 days ago

Post

1572

I've arrived at an interesting result on the current Open LLM leaderboard.
open-llm-leaderboard/open_llm_leaderboard
After I narrowed down the filter of models to be between 8-9B parameters, my recent merge of o1 reasoning models achieved the highest MATH eval result of any Llama 3.x 8B model currently on the board, hitting 33.99%, placing 973/2795.
grimjim/HuatuoSkywork-o1-Llama-3.1-8B

Unfortunately, I need more information to evaluate the parent models used in the merge.
The Skywork/Skywork-o1-Open-Llama-3.1-8B model scored 0% on the MATH eval, which I suspect was due to output formatting that was baked too hard into the model, and placed 2168/2795; the merge achieved a significant uplift in every benchmark across the board.
Unfortunately, FreedomIntelligence/HuatuoGPT-o1-8B was not currently benched as of this post, so I am unable to assess relative benchmarks. Nevertheless, it is intriguing that an ostensibly medical o1 model appears to have resulted in a sizable MATH boost.

grimjim

posted an update 27 days ago

Post

2764

I'm (finally) releasing a Python script that trims excess weights in Gemma2 full-weight models that bloated by ~1B parameters due to an early mergekit bug.
https://github.com/jim-plus/Gemma2-mergekit-remediation

I'd noticed something was off when merges of Gemma2 9B models ended up having ~10B parameters. The current mergekit package is fine, but there are still bloated models on HF that could stand to be fixed.

The script assumes that it will be run from the same directory as the model weights, and will trim the unnecessary lm_head.weight tensor and corresponding index entry.

2 replies

Delta-Vector

in anthracite-org/magnum-v4-12b 30 days ago

repetitive

#9 opened about 1 month ago by

Utochi

Doctor-Shotgun

in anthracite-org/magnum-v4-12b about 1 month ago

Question about the chat_template

#8 opened about 1 month ago by

ZZ12112

grimjim

posted an update about 1 month ago

Post

1408

A reminder that literal base models are valid choices for base model in task arithmetic mergers. Each Instruct or fine-tuned model then becomes a vector against the base model. Example merge formula used can be found via this model page.
grimjim/Magnolia-v3-12B