Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)

Browse Source 
* model: add Tencent Hy 4 (hy_v4) preview architecture support

Adds support for the Tencent Hy 4 model (Hugging Face architecture
HYV4ForCausalLM, GGUF arch hy_v4):

Add HF -> GGUF conversion script (conversion/hy_v4.py) and wire it into the conversion registry
Register hy_v4 GGUF constants, arch enum, and writer support
Implement the hy-v4 model graph, hparams, vocab and context changes
Register the new arch in llama-arch and models registry
Extend arch tests to cover hy_v4

Assisted by Claude Opus 5

* Update convert_hf_to_gguf_update.py

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>

* Update conversion/base.py

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>

* convert : move hy_v4 entry to the same place as in convert_hf_to_gguf_update.py

* model : apply changes related to n_ff_exp becoming per-layer in Hy4-preview

* n_layer_all

---------

Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
HongHuang
2026-09-04 14:31:36 +02:00
committed by GitHub
co-authored by fairydreaming Stanisław Szymczyk Sigbjørn Skjæret
parent 5266f24da7
commit 49c0dc82b8
18 changed files with 1124 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+50
View File
@@ -230,6 +230,8 @@ class Keys:
COUNT = "{arch}.hyper_connection.count"
SINKHORN_ITERATIONS = "{arch}.hyper_connection.sinkhorn_iterations"
EPSILON = "{arch}.hyper_connection.epsilon"
# scale of the post gate (DeepSeek-V4 hardcodes 2.0)
MAGNITUDE = "{arch}.hyper_connection.magnitude"
# absent means the mix projection is full rank (DeepSeek-V4 behaviour)
LOW_RANK = "{arch}.hyper_connection.low_rank"
@@ -592,6 +594,7 @@ class MODEL_ARCH(IntEnum):
HUNYUAN_DENSE = auto()
HUNYUAN_VL = auto()
HY_V3 = auto()
HY_V4 = auto()
SMOLLM3 = auto()
GPT_OSS = auto()
LFM2 = auto()
@@ -1345,6 +1348,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.HUNYUAN_DENSE: "hunyuan-dense",
MODEL_ARCH.HUNYUAN_VL: "hunyuan_vl",
MODEL_ARCH.HY_V3: "hy_v3",
MODEL_ARCH.HY_V4: "hy_v4",
MODEL_ARCH.SMOLLM3: "smollm3",
MODEL_ARCH.GPT_OSS: "gpt-oss",
MODEL_ARCH.LFM2: "lfm2",
@@ -4739,6 +4743,48 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD,
MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
],
MODEL_ARCH.HY_V4: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.HC_HEAD_FN,
MODEL_TENSOR.HC_HEAD_BASE,
MODEL_TENSOR.HC_HEAD_SCALE,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_SINKS,
MODEL_TENSOR.ATTN_Q_A,
MODEL_TENSOR.ATTN_Q_A_NORM,
MODEL_TENSOR.ATTN_Q_B,
MODEL_TENSOR.ATTN_KV_A_MQA,
MODEL_TENSOR.ATTN_KV_A_NORM,
MODEL_TENSOR.ATTN_K_B,
MODEL_TENSOR.ATTN_V_B,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_GATE,
MODEL_TENSOR.INDEXER_K_NORM,
MODEL_TENSOR.INDEXER_PROJ,
MODEL_TENSOR.INDEXER_ATTN_K,
MODEL_TENSOR.INDEXER_ATTN_Q_B,
MODEL_TENSOR.HC_ATTN_FN,
MODEL_TENSOR.HC_ATTN_BASE,
MODEL_TENSOR.HC_ATTN_SCALE,
MODEL_TENSOR.HC_FFN_FN,
MODEL_TENSOR.HC_FFN_BASE,
MODEL_TENSOR.HC_FFN_SCALE,
MODEL_TENSOR.FFN_GATE_INP,
MODEL_TENSOR.FFN_EXP_PROBS_B,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
MODEL_TENSOR.FFN_GATE_SHEXP,
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
],
MODEL_ARCH.SMOLLM3: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
@@ -5438,6 +5484,10 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
MODEL_ARCH.HY_V4: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
MODEL_ARCH.CHATGLM: [
MODEL_TENSOR.ROPE_FREQS,
],