ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)

Browse source 
* GLM-4-0414

* use original one

* Using with tensor map

* fix bug

* change order

* change order

* format with flask8
This commit is contained in:
Yuxuan Zhang 2025-04-11 18:10:10 +08:00 • committed by GitHub
parent 0c50923944
commit 06bb53ad9b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 273 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

19
gguf-py/gguf/constants.py
View file

@ -280,6 +280,7 @@ class MODEL_ARCH(IntEnum):
DEEPSEEK = auto()
DEEPSEEK2 = auto()
CHATGLM = auto()
GLM4 = auto()
BITNET = auto()
T5 = auto()
T5ENCODER = auto()
@ -487,6 +488,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.DEEPSEEK: "deepseek",
MODEL_ARCH.DEEPSEEK2: "deepseek2",
MODEL_ARCH.CHATGLM: "chatglm",
MODEL_ARCH.GLM4: "glm4",
MODEL_ARCH.BITNET: "bitnet",
MODEL_ARCH.T5: "t5",
MODEL_ARCH.T5ENCODER: "t5encoder",
@ -1561,6 +1563,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.GLM4 : [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_POST_NORM,
],
MODEL_ARCH.BITNET: [
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,

8
gguf-py/gguf/tensor_mapping.py
View file

@ -13,7 +13,7 @@ class TensorNameMap:
"transformer.wte", # gpt2 gpt-j mpt refact qwen dbrx jais exaone
"transformer.word_embeddings", # falcon
"word_embeddings", # bloom
"model.embed_tokens", # llama-hf nemotron olmoe olmo2 rwkv6qwen2
"model.embed_tokens", # llama-hf nemotron olmoe olmo2 rwkv6qwen2 glm4-0414
"tok_embeddings", # llama-pth
"embeddings.word_embeddings", # bert nomic-bert
"language_model.embedding.word_embeddings", # persimmon
@ -241,7 +241,8 @@ class TensorNameMap:
),
MODEL_TENSOR.ATTN_POST_NORM: (
"model.layers.{bid}.post_attention_layernorm", # gemma2 olmo2
"model.layers.{bid}.post_attention_layernorm", # gemma2 olmo2 # ge
"model.layers.{bid}.post_self_attn_layernorm", # glm-4-0414
),
# Rotary embeddings
@ -278,6 +279,7 @@ class TensorNameMap:
# Post feed-forward norm
MODEL_TENSOR.FFN_POST_NORM: (
"model.layers.{bid}.post_feedforward_layernorm", # gemma2 olmo2
"model.layers.{bid}.post_mlp_layernorm", # glm-4-0414
),
MODEL_TENSOR.FFN_GATE_INP: (
@ -316,7 +318,7 @@ class TensorNameMap:
"h.{bid}.mlp.c_fc", # gpt2
"transformer.h.{bid}.mlp.fc1", # phi2
"model.layers.{bid}.mlp.fc1", # phi2
"model.layers.{bid}.mlp.gate_up_proj", # phi3
"model.layers.{bid}.mlp.gate_up_proj", # phi3 glm-4-0414
"model.layers.layers.{bid}.mlp.up_proj", # plamo
"model.layers.{bid}.feed_forward.w3", # internlm2
"encoder.layers.{bid}.mlp.fc11", # nomic-bert