Text Generation
Transformers
GGUF
TensorBoard
Safetensors
mistral
quantized
2-bit
3-bit
4-bit precision
5-bit
6-bit
8-bit precision
GGUF
gemma
alignment-handbook
trl
dpo
generated_from_trainer
conversational
dataset:argilla/dpo-mix-7k
arxiv:2310.16944
Eval Results
Inference Endpoints
has_space
text-generation-inference
error with llama.cpp
#2
by
jordigonzm
- opened
Getting this error with llama.cpp
cpu_avx2/libext_server.so exception create_tensor: tensor 'blk.0.attn_q.weight' has wrong shape; expected 3072, 3072, got 3072, 4096, 1, 1"