Jim Lai
grimjim
AI & ML interests
Experimenting primarily with 7B-12B parameter text completion models. Not all models are intended for direct use, but aim for research and/or educational purposes.
Recent Activity
posted
an
update
3 days ago
This recent paper points to an explanation for the unreasonable effectiveness of Frankenmerges: https://huggingface.co/papers/2502.05171
Specifically, the duplication of layers in Frankenmerges serves a purpose similar to what occurs in their recurrent-depth architecture. Successful frankenmerges that operate without additional fine-tuning are able to recover or "heal" from any damage due to abrupt transitions between layer blocks. Operational replicated layer blocks can provide functional benefits grounded in latent reasoning. Frankenmerges can also result in hybrid reasoning, by splicing together the latent reasoning of different models.
Back in April 2024, I was able to duplicate a few layers in the Llama 3 8B model, turning it into a 9B model, without harming benchmarks significantly, despite any transition damage.
https://huggingface.co/grimjim/llama-3-experiment-v1-9B
My informal experimentation suggested that latent reasoning circuits could occupy continguous stacks of 2-4 layers, though the result was highly sensitive to the choice of transition location between layers.
updated
a model
3 days ago
grimjim/Magnolia-v5-12B
Organizations
grimjim's activity
Spurious `trust_remote_code=True` objection when submitting a model?
#1100 opened 3 days ago
by
grimjim
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65c992424936ab38ecf706b0/aq7vuHFPO1S93fwJk0Cuq.jpeg)
Adding Evaluation Results
#1 opened 9 days ago
by
T145
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/rv3XTyO6TSLNmebutG9wy.png)
SLERP merge example code?
3
#20 opened 7 months ago
by
grimjim
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65c992424936ab38ecf706b0/aq7vuHFPO1S93fwJk0Cuq.jpeg)
Adding Evaluation Results
#1 opened 20 days ago
by
T145
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/rv3XTyO6TSLNmebutG9wy.png)
Please submit this model to the Open LLM Leaderboard
3
#1 opened about 1 month ago
by
grimjim
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65c992424936ab38ecf706b0/aq7vuHFPO1S93fwJk0Cuq.jpeg)
Adding Evaluation Results
#1 opened about 1 month ago
by
T145
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/rv3XTyO6TSLNmebutG9wy.png)
Adding Evaluation Results
#2 opened 4 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#3 opened 4 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#6 opened 4 months ago
by
kirin7
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6423d0906e61cda1b3a40049/SObDt80dzw1zcTTAjQ0Ol.jpeg)
Adding Evaluation Results
#4 opened 5 months ago
by
CombinHorizon
[bot] Conversion to Parquet
#1 opened 5 months ago
by
parquet-converter
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1658495802629-61f02cf649ea1fb7363729dc.png)
Adding Evaluation Results
#1 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#2 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
fp16 version?
2
#2 opened 5 months ago
by
Tycho-S
Adding Evaluation Results
#3 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#1 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#1 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#8 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#1 opened 5 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
q8 gives error in LM studio: "Checksum failed file corrupted"
3
#1 opened 6 months ago
by
tazztone