CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-07 09:57:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-07-09 09:38:48 -04:00
parent f7c7a926f0 26a48ad699
commit a60a24beed
9 changed files with 608 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
gguf-py/gguf/constants.py
View File

@@ -288,6 +288,7 @@ class MODEL_ARCH(IntEnum):
LLAMA4 = auto()
DECI = auto()
FALCON = auto()
FALCON_H1 = auto()
BAICHUAN = auto()
GROK = auto()
GPT2 = auto()
@@ -667,6 +668,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.DOTS1: "dots1",
MODEL_ARCH.ARCEE: "arcee",
MODEL_ARCH.ERNIE4_5: "ernie4_5",
MODEL_ARCH.FALCON_H1: "falcon-h1",
MODEL_ARCH.HUNYUAN_MOE: "hunyuan-moe",
MODEL_ARCH.SMOLLM3: "smollm3",
}
@@ -2251,6 +2253,40 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.FALCON_H1: [
# Token embedding
MODEL_TENSOR.TOKEN_EMBD,
# Input layernorm
MODEL_TENSOR.ATTN_NORM,
# Attention components
MODEL_TENSOR.ATTN_Q, # Query projection
MODEL_TENSOR.ATTN_K, # Key projection
MODEL_TENSOR.ATTN_V, # Value projection
MODEL_TENSOR.ATTN_OUT, # Output projection
# SSM components (Mamba2 specific)
MODEL_TENSOR.SSM_IN, # Input projection for SSM
MODEL_TENSOR.SSM_CONV1D, # Convolution layer
MODEL_TENSOR.SSM_DT, # Delta time projection
MODEL_TENSOR.SSM_A, # A parameter (log form)
MODEL_TENSOR.SSM_D, # D parameter
MODEL_TENSOR.SSM_NORM, # Normalization in SSM
MODEL_TENSOR.SSM_OUT, # Output projection
# Pre-feedforward layernorm
MODEL_TENSOR.FFN_PRE_NORM,
# Feed-forward network components
MODEL_TENSOR.FFN_GATE, # Gate projection (SwiGLU)
MODEL_TENSOR.FFN_DOWN, # Down projection
MODEL_TENSOR.FFN_UP, # Up projection
# Post-feedforward layernorm
MODEL_TENSOR.OUTPUT_NORM, # Final layer norm
MODEL_TENSOR.OUTPUT, # Output projection (lm_head)
],
MODEL_ARCH.HUNYUAN_MOE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,