Quantized versions of Prometheus 2 - an alternative of GPT-4 evaluation when doing fine-grained evaluation of an underlying LLM.
Seva Leonov PRO
vsevolodl
AI & ML interests
ML Ops, scalable Inference, quantization, long context, fine-tuning
Recent Activity
liked
a model
17 days ago
cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic
upvoted
a
collection
about 1 month ago
Llama 3.3
liked
a model
about 1 month ago
NexaAIDev/OmniAudio-2.6B
Organizations
models
14
vsevolodl/Llama-3-8B-Instruct-Gradient-4194k-GGUF
Updated
•
30
•
1
vsevolodl/Yi-1.5-34B-Chat-GGUF
Updated
•
21
•
1
vsevolodl/falcon-11B-GGUF
Updated
•
18
•
1
vsevolodl/Yi-1.5-9B-Chat-GGUF
Updated
•
19
•
1
vsevolodl/Llama-3-70B-Instruct-Gradient-1048k-GGUF
Text Generation
•
Updated
•
112
•
3
vsevolodl/Llama-3-8B-Instruct-Gradient-1048k-GGUF
Text Generation
•
Updated
•
22
•
1
vsevolodl/prometheus-8x7b-v2.0-GGUF
Text2Text Generation
•
Updated
•
27
•
3
vsevolodl/prometheus-7b-v2.0-GGUF
Text2Text Generation
•
Updated
•
35
•
4
vsevolodl/mistral_b_finance_finetuned_test
Updated
vsevolodl/outputs_mistral_b_finance_finetuned_test
Updated