Evgeniy Hristoforu's picture

Evgeniy Hristoforu

ehristoforu

·

https://civitai.com/user/ehristoforu

AI & ML interests

Diffusers, LLM and others ML.

Recent Activity

replied to their post 4 days ago

Introducing our first standalone model – FluentlyLM Prinum Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one. General characteristics: - Model type: Causal language models (QwenForCausalLM, LM Transformer) - Number of parameters: 32.5B - Number of parameters (not embedded): 31.0B - Number of layers: 64 - Context: 131,072 tokens - Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported) - License: MIT Creation strategy: The basis of the strategy is shown in Pic. 2. We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers. Evolution: 🏆 12th place in the Open LLM Leaderboard (https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard#) (21.02.2025) Detailed results and comparisons are presented in Pic. 3. Links: - Model: https://huggingface.co./fluently-lm/FluentlyLM-Prinum - GGUF version: https://huggingface.co./mradermacher/FluentlyLM-Prinum-GGUF - Demo on ZeroGPU: https://huggingface.co./spaces/ehristoforu/FluentlyLM-Prinum-demo

reacted to their post with 🔥 4 days ago

Introducing our first standalone model – FluentlyLM Prinum Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one. General characteristics: - Model type: Causal language models (QwenForCausalLM, LM Transformer) - Number of parameters: 32.5B - Number of parameters (not embedded): 31.0B - Number of layers: 64 - Context: 131,072 tokens - Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported) - License: MIT Creation strategy: The basis of the strategy is shown in Pic. 2. We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers. Evolution: 🏆 12th place in the Open LLM Leaderboard (https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard#) (21.02.2025) Detailed results and comparisons are presented in Pic. 3. Links: - Model: https://huggingface.co./fluently-lm/FluentlyLM-Prinum - GGUF version: https://huggingface.co./mradermacher/FluentlyLM-Prinum-GGUF - Demo on ZeroGPU: https://huggingface.co./spaces/ehristoforu/FluentlyLM-Prinum-demo

posted an update 4 days ago

Introducing our first standalone model – FluentlyLM Prinum Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one. General characteristics: - Model type: Causal language models (QwenForCausalLM, LM Transformer) - Number of parameters: 32.5B - Number of parameters (not embedded): 31.0B - Number of layers: 64 - Context: 131,072 tokens - Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported) - License: MIT Creation strategy: The basis of the strategy is shown in Pic. 2. We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers. Evolution: 🏆 12th place in the Open LLM Leaderboard (https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard#) (21.02.2025) Detailed results and comparisons are presented in Pic. 3. Links: - Model: https://huggingface.co./fluently-lm/FluentlyLM-Prinum - GGUF version: https://huggingface.co./mradermacher/FluentlyLM-Prinum-GGUF - Demo on ZeroGPU: https://huggingface.co./spaces/ehristoforu/FluentlyLM-Prinum-demo

View all activity

Organizations

ehristoforu's activity

New activity in fluently-lm/FluentlyLM-Prinum 8 days ago

Adding Evaluation Results

#1 opened 8 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 10 days ago

🚩 Report: Not working

#1106 opened 11 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 21 days ago

! Eval error in Llama3.3 70b based model

#1089 opened 23 days ago by

no Eval for L3.3 70b based model

#1091 opened 21 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 22 days ago

🚩 Report: Not working

#1084 opened 27 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 25 days ago

Model results missing

#1075 opened about 1 month ago by

New activity in ehristoforu/fd-lora-merged-16x32 25 days ago

Adding Evaluation Results

#1 opened 25 days ago by

New activity in ehristoforu/fd-lora-merged-64x128 25 days ago

Adding Evaluation Results

#1 opened 25 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 25 days ago

🚩 Report: Not working

#1086 opened 25 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 29 days ago

🚩 Report: Not working

#1082 opened 30 days ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 1 month ago

Qwen2.5-32B merge eval error

#1078 opened about 1 month ago by

New activity in llamafy/README about 2 months ago

Model Request: CohereForAI/c4ai-command-r7b-12-2024

#1 opened about 2 months ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 2 months ago

[Feature] Remove "model voting"

#1059 opened about 2 months ago by

⌛ Too long a process of evolution

#1058 opened about 2 months ago by

New activity in open-llm-leaderboard/comparator about 2 months ago

🚩 Report: Not working

#2 opened about 2 months ago by

New activity in BBQQYT/Ai_for_detecting_r34 about 2 months ago

Где обещанный датасет?

#1 opened about 2 months ago by

New activity in fluently-sets/reasoning-1-1k-demo 2 months ago

Adding `safetensors` variant of this model

#1 opened 2 months ago by

New activity in PR-Puppets/PR-Puppet-Sora 3 months ago

🚩 Report: Legal issue(s)

#34 opened 3 months ago by

New activity in ehristoforu/HappyLlama1 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

leaderboard-pr-bot

New activity in synergetic/FrankenQwen2.5-14B 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

leaderboard-pr-bot