Expose halo's [fast] MoE preset through the LiteLLM gateway and make it the rag CLI's default chat model (overridable via RAG_CHAT_MODEL), so query synthesis is quicker than the larger coder model. |
||
|---|---|---|
| .. | ||
| amd | ||
| attic | ||
| halo | ||
| mx | ||
| nixtee1 | ||
| sgx | ||
| t15 | ||
| x1 | ||
Expose halo's [fast] MoE preset through the LiteLLM gateway and make it the rag CLI's default chat model (overridable via RAG_CHAT_MODEL), so query synthesis is quicker than the larger coder model. |
||
|---|---|---|
| .. | ||
| amd | ||
| attic | ||
| halo | ||
| mx | ||
| nixtee1 | ||
| sgx | ||
| t15 | ||
| x1 | ||