top | item 39179521 (no title) keriati1 | 2 years ago We actually run already in-house ollama server prototype for coding assistance with deepseek coder and it is pretty good. Now if we would get a model for this, that is on chatgpt 4 level, I would be super happy. discuss order hn newest eurekin|2 years ago Did you finetune a model? keriati1|2 years ago No, we went with RAG pipeline approach as we assume things change too fast. load replies (1)
eurekin|2 years ago Did you finetune a model? keriati1|2 years ago No, we went with RAG pipeline approach as we assume things change too fast. load replies (1)
keriati1|2 years ago No, we went with RAG pipeline approach as we assume things change too fast. load replies (1)
eurekin|2 years ago
keriati1|2 years ago