model : update label for LFM2-24B-A2B (#19848)

* model : Update label for LFM2-24B-A2B

```
❯ build/bin/llama-bench -m /data/playground/checkpoints/LFM2-24B-A2B-Preview-Q4_0.gguf,/data/playground/checkpoints/LFM2-8B-A1B-Q4_0.gguf -p 1 -n 0
| model                          |       size |     params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| lfm2moe 24B.A2B Q4_0           |  12.54 GiB |    23.84 B | CPU        |      10 |             pp1 |         30.35 ± 2.49 |
| lfm2moe 8B.A1B Q4_0            |   4.41 GiB |     8.34 B | CPU        |      10 |             pp1 |         49.24 ± 1.93 |
```

* Remove extra line
This commit is contained in:
Tarek Dakhran 2026-02-24 14:27:42 +01:00 committed by GitHub
parent c830f99cfa
commit da426cb250
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 1 deletions

View File

@ -123,6 +123,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_8B_A1B: return "8B.A1B";
case LLM_TYPE_16B_A1B: return "16B.A1B";
case LLM_TYPE_21B_A3B: return "21B.A3B";
case LLM_TYPE_24B_A2B: return "24B.A2B";
case LLM_TYPE_30B_A3B: return "30B.A3B";
case LLM_TYPE_31B_A3_5B: return "31B.A3.5B";
case LLM_TYPE_35B_A3B: return "35B.A3B";
@ -2381,7 +2382,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
hparams.recurrent_layer_arr[il] = hparams.n_head_kv(il) == 0;
}
type = LLM_TYPE_8B_A1B;
switch (hparams.n_layer) {
case 24: type = LLM_TYPE_8B_A1B; break;
case 40: type = LLM_TYPE_24B_A2B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_SMALLTHINKER:
{

View File

@ -116,6 +116,7 @@ enum llm_type {
LLM_TYPE_8B_A1B, // lfm2moe
LLM_TYPE_16B_A1B,
LLM_TYPE_21B_A3B, // Ernie MoE small
LLM_TYPE_24B_A2B, // lfm2moe
LLM_TYPE_30B_A3B,
LLM_TYPE_31B_A3_5B,
LLM_TYPE_35B_A3B, // Qwen3.5