Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0BZN-LLM-v1
Modelo de linguagem proprietário desenvolvido por Fernando Bolzan, especializado em código e raciocínio. Não temos detalhes públicos sobre arquitetura interna ou dados exatos de treinamento.
- Base: Qwen2.5-Coder-7B-Instruct (Apache 2.0)
- Treinamento: QLoRA
- Hardware: RTX 3060 12GB
- Formatos:
safetensors(Transformers)bzn-llm-v1-bf16.gguf(15.2 GB - Qualidade Máxima)bzn-llm-v1-q5_k_m.gguf(5.2 GB - Alta Qualidade, Leve)bzn-llm-v1-q4_k_m.gguf(4.5 GB - Bom custo-benefício)
Uso com Ollama
Para usar a versão GGUF diretamente no Ollama (0.30+):
bash
ollama run hf.co/fbolzan/BZN-LLM-v1
Uso com Transformers
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("fbolzan/BZN-LLM-v1")tokenizer = AutoTokenizer.from_pretrained("fbolzan/BZN-LLM-v1")
Model provider
fbolzan
Model tree
Base
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information