Here you can find all the new Calme-3 models
Maziyar Panahi PRO
MaziyarPanahi
AI & ML interests
Fine-Tuning, RLHF, Merging, Quantizations, Leaderboards
Recent Activity
replied to
sometimesanotion's
post
about 2 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 7 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 7 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
Collections
20
My experiments with Llama-3 models
-
MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF
Text Generation • Updated • 223k • 167 -
MaziyarPanahi/calme-2.1-llama3-70b
Text Generation • Updated • 58 • 7 -
MaziyarPanahi/calme-2.2-llama3-70b
Text Generation • Updated • 3.23k • 17 -
MaziyarPanahi/calme-2.3-llama3-70b
Text Generation • Updated • 1.67k • 4
spaces
6
pinned
Running
on
Zero
74
Qwen2-VL-2B
🔥
Generate text from images and videos
pinned
Running
on
Zero
219
Phi 3.5 Vision
🔥
Generate text from an image and question
pinned
Running
on
Zero
46
Microsoft Phi-3 Vision 128k
🔥
Microsoft Phi-3 Vision 128k with Multimodal capabilities
pinned
Running
on
Zero
87
Llava Llama-3 8B
🔥
Meta Llama3 8b with Llava Multimodal capabilities
Running
4
Chat With Phi 2
🚀
Generate chat responses with customizable prompts and settings
Running
4
Chat With Mistral
🔥
Generate chat responses based on user input
models
2683

MaziyarPanahi/WizardLM-2-8x22B-AWQ
Text Generation
•
Updated
•
1.8k
•
12

MaziyarPanahi/Sombrero-Opus-14B-Elite6-GGUF
Text Generation
•
Updated
•
107

MaziyarPanahi/LLaMA-3-8B-GRPO-Finance-Math-TR-GGUF
Text Generation
•
Updated
•
113

MaziyarPanahi/ZYH-LLM-Qwen2.5-14B-V3-GGUF
Text Generation
•
Updated
•
96

MaziyarPanahi/DeepSeek-R1-Distill-Llama-3B-GGUF
Text Generation
•
Updated
•
94

MaziyarPanahi/Clarus-7B-v0.1-GGUF
Text Generation
•
Updated
•
101

MaziyarPanahi/Qwen2.5-14B-CIC-SciCite-GGUF
Text Generation
•
Updated
•
111

MaziyarPanahi/Qwen2.5-14B-CIC-ACLARC-GGUF
Text Generation
•
Updated
•
102

MaziyarPanahi/Viper-Coder-HybridMini-v1.3-GGUF
Text Generation
•
Updated
•
109
•
1

MaziyarPanahi/Llama-3.1-TAIDE-R1-8B-Chat-GGUF
Text Generation
•
Updated
•
151
datasets
41
MaziyarPanahi/SYNTHETIC-1-1.6M
Viewer
•
Updated
•
1.6M
•
52
MaziyarPanahi/SYNTHETIC-1-800K
Viewer
•
Updated
•
798k
•
15
MaziyarPanahi/SYNTHETIC-1-200K
Viewer
•
Updated
•
199k
•
16
MaziyarPanahi/MATH-lighteval
Viewer
•
Updated
•
25k
•
247
•
2
MaziyarPanahi/synthetic-medical-conversations-deepseek-v3-chat
Viewer
•
Updated
•
4.55k
•
128
•
6
MaziyarPanahi/llama-3.1-tulu-3-70b-preference-mixture
Viewer
•
Updated
•
334k
•
112
MaziyarPanahi/M2Lingual-sharegpt
Viewer
•
Updated
•
174k
•
53
•
2
MaziyarPanahi/open-perfectblend-fixed
Viewer
•
Updated
•
1.36M
•
125
•
4
MaziyarPanahi/orca-agentinstruct-1M-v1-cleaned-fixed-sharegpt
Viewer
•
Updated
•
1.05M
•
214
•
4
MaziyarPanahi/Magpie-Qwen2.5-Pro-1M-v0.1-medium-good
Viewer
•
Updated
•
425k
•
117
•
1