GarandPLG
68ed6d035e
Update default model provider to “Cerebras PAUG”. Reorganize the Cerebras language‑model configuration into two groups – “Cerebras FREE” and “Cerebras PAUG” – each with its own model list and adjusted token limits.
159 lines
4.2 KiB
Nix
159 lines
4.2 KiB
Nix
_: {
|
|
programs.zed-editor.userSettings.language_models.openai_compatible = {
|
|
"Cerebras FREE" = {
|
|
api_url = "https://api.cerebras.ai/v1";
|
|
available_models = [
|
|
{
|
|
name = "gpt-oss-120b";
|
|
display_name = "OpenAI GPT OSS";
|
|
max_tokens = 65000;
|
|
max_output_tokens = 32000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = false;
|
|
};
|
|
}
|
|
{
|
|
name = "zai-glm-4.7";
|
|
display_name = "Z.ai GLM 4.7";
|
|
max_tokens = 64000;
|
|
max_output_tokens = 40000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "llama3.1-8b";
|
|
display_name = "Llama 3.1 8B";
|
|
max_tokens = 8000;
|
|
max_output_tokens = 8000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "llama-3.3-70b";
|
|
display_name = "Llama 3.3 70B";
|
|
max_tokens = 65000;
|
|
max_output_tokens = 8000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "qwen-3-32b";
|
|
display_name = "Qwen 3 32B";
|
|
max_tokens = 65000;
|
|
max_output_tokens = 8000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = false;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "qwen-3-235b-a22b-instruct-2507";
|
|
display_name = "Qwen 3 235B Instruct";
|
|
max_tokens = 65000;
|
|
max_output_tokens = 32000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = false;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
];
|
|
};
|
|
"Cerebras PAUG" = {
|
|
api_url = "https://api.cerebras.ai/v1";
|
|
available_models = [
|
|
{
|
|
name = "gpt-oss-120b";
|
|
display_name = "OpenAI GPT OSS";
|
|
max_tokens = 131000;
|
|
max_output_tokens = 40000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = false;
|
|
};
|
|
}
|
|
{
|
|
name = "zai-glm-4.7";
|
|
display_name = "Z.ai GLM 4.7";
|
|
max_tokens = 131000;
|
|
max_output_tokens = 40000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "llama3.1-8b";
|
|
display_name = "Llama 3.1 8B";
|
|
max_tokens = 32000;
|
|
max_output_tokens = 8000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "llama-3.3-70b";
|
|
display_name = "Llama 3.3 70B";
|
|
max_tokens = 128000;
|
|
max_output_tokens = 65000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = true;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "qwen-3-32b";
|
|
display_name = "Qwen 3 32B";
|
|
max_tokens = 131000;
|
|
max_output_tokens = 8000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = false;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
{
|
|
name = "qwen-3-235b-a22b-instruct-2507";
|
|
display_name = "Qwen 3 235B Instruct";
|
|
max_tokens = 131000;
|
|
max_output_tokens = 40000;
|
|
capabilities = {
|
|
tools = true;
|
|
images = true;
|
|
parallel_tool_calls = false;
|
|
prompt_cache_key = true;
|
|
};
|
|
}
|
|
];
|
|
};
|
|
};
|
|
}
|