chore(llm): update llama-cpp, llama-swap and switch to qwen3.5-27b-thinking
- Bump llama-cpp from version 8157 to 8196 - Bump llama-swap from version 192 to 197 - Switch default assistant model from qwen3-coder-next-80b to qwen3.5-27b-thinking - Remove glm-4-32b-instruct model configuration - Update qwen3.5-27b-thinking config: - Use bartowski quantization (IQ4_XS) instead of unsloth - Increase context window from 131k to 196k - Add cache type settings (q8_0) and CUDA device - Add 1password-cli to home-manager programs - Fix typo: 'dispay' -> 'display' in llm-config.lua
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
local llm_endpoint = "https://llm-api.va.reichard.io"
|
||||
local llm_assistant_model = "qwen3-coder-next-80b-instruct"
|
||||
local llm_assistant_model = "qwen3.5-27b-thinking"
|
||||
local llm_infill_model = llm_assistant_model
|
||||
local current_fim = "copilot"
|
||||
|
||||
@@ -63,7 +63,7 @@ codecompanion.setup({
|
||||
inline = { adapter = "llamaswap" },
|
||||
cmd = { adapter = "llamaswap" },
|
||||
},
|
||||
chat = { dispay = "telescope" },
|
||||
chat = { display = "telescope" },
|
||||
memory = { opts = { chat = { enabled = true } } },
|
||||
})
|
||||
|
||||
|
||||
Reference in New Issue
Block a user