SYNTHETIC-1
Collection
A collection of tasks & verifiers for reasoning datasets
•
9 items
•
Updated
•
48
Maziyar Panahi PRO
MaziyarPanahi
AI & ML interests
Fine-Tuning, RLHF, Merging, Quantizations, Leaderboards
Recent Activity
replied to
sometimesanotion's
post
about 6 hours ago
I'd like to draw your attention to a Lamarck-based experiment which uses Arcee AI's newly published arcee_fusion merge method for three out of its four merges. Yes, just four. This is a simple one, and its recipe is fully open:
https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7-Fusion
It unifies three branches, all of which feature models which bring Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose together. One side features @jpacifico's http://huggingface.co/jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 and the other features @suayptalha's http://huggingface.co/suayptalha/Lamarckvergence-14B paired with my models which were their merge ancestors.
A fusion merge - of a fusion merge and a SLERP of a fusion and older merge - should demonstrate the new merge method's behavior in interesting ways, especially in the first 1/4th of the model where the SLERP has less impact.
I welcome you to kick the tires and learn from it. It has prose quality near Qwenvergence v12's - as you'd expect.
Thank you, @mradermacher and @MaziyarPanahi, for the first-day quantizations! Your work helped get me started. https://huggingface.co/models?other=base_model:quantized:sometimesanotion/Lamarck-14B-v0.7-Fusion
replied to
sometimesanotion's
post
about 11 hours ago
I'd like to draw your attention to a Lamarck-based experiment which uses Arcee AI's newly published arcee_fusion merge method for three out of its four merges. Yes, just four. This is a simple one, and its recipe is fully open:
https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7-Fusion
It unifies three branches, all of which feature models which bring Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose together. One side features @jpacifico's http://huggingface.co/jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 and the other features @suayptalha's http://huggingface.co/suayptalha/Lamarckvergence-14B paired with my models which were their merge ancestors.
A fusion merge - of a fusion merge and a SLERP of a fusion and older merge - should demonstrate the new merge method's behavior in interesting ways, especially in the first 1/4th of the model where the SLERP has less impact.
I welcome you to kick the tires and learn from it. It has prose quality near Qwenvergence v12's - as you'd expect.
Thank you, @mradermacher and @MaziyarPanahi, for the first-day quantizations! Your work helped get me started. https://huggingface.co/models?other=base_model:quantized:sometimesanotion/Lamarck-14B-v0.7-Fusion
reacted
to
sometimesanotion's
post
with 🔥
about 11 hours ago
I'd like to draw your attention to a Lamarck-based experiment which uses Arcee AI's newly published arcee_fusion merge method for three out of its four merges. Yes, just four. This is a simple one, and its recipe is fully open:
https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7-Fusion
It unifies three branches, all of which feature models which bring Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose together. One side features @jpacifico's http://huggingface.co/jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 and the other features @suayptalha's http://huggingface.co/suayptalha/Lamarckvergence-14B paired with my models which were their merge ancestors.
A fusion merge - of a fusion merge and a SLERP of a fusion and older merge - should demonstrate the new merge method's behavior in interesting ways, especially in the first 1/4th of the model where the SLERP has less impact.
I welcome you to kick the tires and learn from it. It has prose quality near Qwenvergence v12's - as you'd expect.
Thank you, @mradermacher and @MaziyarPanahi, for the first-day quantizations! Your work helped get me started. https://huggingface.co/models?other=base_model:quantized:sometimesanotion/Lamarck-14B-v0.7-Fusion
Organizations
MaziyarPanahi's activity
upvoted
a
collection
3 days ago
upvoted
an
article
11 days ago
Article
Fixing Open LLM Leaderboard with Math-Verify
•
25
upvoted
a
paper
11 days ago
upvoted
an
article
12 days ago
Article
From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub
•
49
upvoted
a
collection
18 days ago
upvoted
a
collection
21 days ago
upvoted
a
collection
23 days ago
upvoted
an
article
23 days ago
Article
Open-R1: Update #1
By
and 7 others
•
•
287
upvoted
a
collection
29 days ago
upvoted
an
article
29 days ago
Article
We now support VLMs in smolagents!
•
86
upvoted
a
paper
about 1 month ago
upvoted
an
article
about 1 month ago
Article
Introducing the Synthetic Data Generator - Build Datasets with Natural Language
•
107
upvoted
a
paper
about 1 month ago
upvoted
an
article
about 1 month ago
Article
Train 400x faster Static Embedding Models with Sentence Transformers
•
149
upvoted
a
collection
about 1 month ago
upvoted
an
article
about 1 month ago
Article
Mastering Tensor Dimensions in Transformers
By
•
•
44
upvoted
2
collections
about 2 months ago
upvoted
a
collection
2 months ago
upvoted
an
article
2 months ago
Article
Introduction to Quantization cooked in 🤗 with 💗🧑🍳
By
•
•
28