CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

add LLM_ARCH_STARCODER to llama.cpp

Browse Source
This commit is contained in:
Meng Zhang
2023-09-15 11:45:26 +08:00
parent 7e0a843b6a
commit 7298c37e7e
1 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
llama.cpp
View File

@@ -378,6 +378,21 @@ static std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NAMES =
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
},
},
{
LLM_ARCH_STARCODER,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_POS_EMBD, "position_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_OUTPUT, "output" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" },
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
},
},
{
LLM_ARCH_UNKNOWN,
{
@@ -897,6 +912,7 @@ static llama_state g_state;
// available llama models
enum e_model {
MODEL_UNKNOWN,
MODEL_1B,
MODEL_3B,
MODEL_7B,
MODEL_13B,
@@ -1715,6 +1731,14 @@ static void llm_load_hparams(
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
case LLM_ARCH_STARCODER:
{
GGUF_GET_KEY(ctx, hparams.f_norm_eps, gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, kv(LLM_KV_ATTENTION_LAYERNORM_EPS));
switch (hparams.n_layer) {
case 24: model.type = e_model::MODEL_1B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
default: (void)0;
};