CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add LLaDA 8b Diffusion model (#14771)

Browse Source 
* Add support for Llada-8b: diffusion model

* Add README

* Fix README and convert_hf_to_gguf

* convert_hf_to_gguf.py: address review comments

* Make everything in a single example

* Remove model-specific sampling

* Remove unused argmax

* Remove braced initializers, improve README.md a bit

* Add diffusion specific gguf params in set_vocab, remove setting rope_theta and rms_norm_eps

* Remove adding the mask token

* Move add_add_bos_token to set_vocab

* use add_bool in gguf_writer.py
This commit is contained in:
Aman Gupta
2025-07-31 19:49:09 +08:00
committed by GitHub
parent 11490b3672
commit 8a4a856277
12 changed files with 931 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src/llama-arch.cpp
View File

@@ -89,6 +89,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_LFM2, "lfm2" },
{ LLM_ARCH_DREAM, "dream" },
{ LLM_ARCH_SMALLTHINKER, "smallthinker" },
{ LLM_ARCH_LLADA, "llada" },
{ LLM_ARCH_UNKNOWN, "(unknown)" },
};
@@ -1972,6 +1973,23 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
},
},
{
LLM_ARCH_LLADA,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_OUTPUT, "output" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
{ LLM_TENSOR_ATTN_K, "blk.%d.attn_k" },
{ LLM_TENSOR_ATTN_V, "blk.%d.attn_v" },
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
{ LLM_TENSOR_FFN_GATE, "blk.%d.ffn_gate" },
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
},
},
{
LLM_ARCH_UNKNOWN,
{
@@ -2224,6 +2242,7 @@ bool llm_arch_is_hybrid(const llm_arch & arch) {
bool llm_arch_is_diffusion(const llm_arch & arch) {
switch (arch) {
case LLM_ARCH_DREAM:
case LLM_ARCH_LLADA:
return true;
default:
return false;