nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 18 Packages Projects Releases Wiki Activity

llama : add support for NVIDIA Nemotron 3 Nano (#18058)

Browse Source 
* llama : add support for NVIDIA Nemotron Nano 3

This commit adds support for the NVIDIA Nemotron Nano 3 model, enabling
the conversion and running of this model.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Daniel Bevenius
2025-12-16 07:19:26 +01:00
committed by GitHub
co-authored by Georgi Gerganov
parent 40d9c394f4
commit 2995341730
9 changed files with 267 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+29
View File
@@ -413,6 +413,7 @@ class MODEL_ARCH(IntEnum):
JAIS = auto()
NEMOTRON = auto()
NEMOTRON_H = auto()
NEMOTRON_H_MOE = auto()
EXAONE = auto()
EXAONE4 = auto()
GRANITE = auto()
@@ -786,6 +787,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.JAIS: "jais",
MODEL_ARCH.NEMOTRON: "nemotron",
MODEL_ARCH.NEMOTRON_H: "nemotron_h",
MODEL_ARCH.NEMOTRON_H_MOE: "nemotron_h_moe",
MODEL_ARCH.EXAONE: "exaone",
MODEL_ARCH.EXAONE4: "exaone4",
MODEL_ARCH.GRANITE: "granite",
@@ -2529,6 +2531,33 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.NEMOTRON_H_MOE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.SSM_IN,
MODEL_TENSOR.SSM_CONV1D,
MODEL_TENSOR.SSM_DT,
MODEL_TENSOR.SSM_A,
MODEL_TENSOR.SSM_D,
MODEL_TENSOR.SSM_NORM,
MODEL_TENSOR.SSM_OUT,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
# experts
MODEL_TENSOR.FFN_GATE_INP,
MODEL_TENSOR.FFN_UP_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
# shared expert
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
MODEL_TENSOR.FFN_EXP_PROBS_B,
],
MODEL_ARCH.EXAONE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
gguf-py/gguf/tensor_mapping.py
+7 -2
View File
@@ -379,6 +379,7 @@ class TensorNameMap:
"model.layers.{bid}.feed_forward.gate", # lfm2moe
"model.layers.{bid}.mlp.router.gate", # afmoe
"layers.{bid}.gate", # mistral-large
"backbone.layers.{bid}.mixer.gate", # nemotron-h-moe
),
MODEL_TENSOR.FFN_GATE_INP_SHEXP: (
@@ -392,6 +393,7 @@ class TensorNameMap:
"model.layers.{bid}.mlp.expert_bias", # afmoe
"model.layers.{bid}.feed_forward.expert_bias", # lfm2moe
"model.layers.{bid}.block_sparse_moe.e_score_correction", # minimax-m2
"backbone.layers.{bid}.mixer.gate.e_score_correction" # nemotron-h-moe
),
# Feed-forward up
@@ -440,7 +442,7 @@ class TensorNameMap:
"layers.{bid}.feed_forward.experts.w3", # mixtral (merged)
"transformer.decoder_layer.{bid}.moe.linear_v", # Grok (merged)
"transformer.blocks.{bid}.ffn.experts.mlp.v1", # dbrx
"model.layers.{bid}.mlp.experts.up_proj", # qwen2moe olmoe (merged) ernie4.5-moe
"model.layers.{bid}.mlp.experts.up_proj", # qwen2moe olmoe (merged) ernie4.5-moe, nemotron-h-moe (merged)
"model.layers.{bid}.block_sparse_moe.experts.w3", # phimoe (merged)
"model.layers.{bid}.feed_forward.experts.up_proj", # llama4
"encoder.layers.{bid}.mlp.experts.mlp.w1", # nomic-bert-moe
@@ -454,6 +456,7 @@ class TensorNameMap:
"model.layers.{bid}.feed_forward.down_proj",
"model.layers.{bid}.mlp.shared_mlp.up_proj", # hunyuan
"layers.{bid}.shared_experts.w3", # mistral-large
"backbone.layers.{bid}.mixer.shared_experts.up_proj", # nemotron-h-moe
),
MODEL_TENSOR.FFN_UP_CHEXP: (
@@ -548,7 +551,7 @@ class TensorNameMap:
"layers.{bid}.feed_forward.experts.w2", # mixtral (merged)
"transformer.decoder_layer.{bid}.moe.linear_1", # Grok (merged)
"transformer.blocks.{bid}.ffn.experts.mlp.w2", # dbrx
"model.layers.{bid}.mlp.experts.down_proj", # qwen2moe olmoe (merged) ernie4.5-moe
"model.layers.{bid}.mlp.experts.down_proj", # qwen2moe olmoe (merged) ernie4.5-moe nemotron-h-moe (merged)
"model.layers.{bid}.block_sparse_moe.output_linear", # granitemoe
"model.layers.{bid}.block_sparse_moe.experts.w2", # phimoe (merged)
"model.layers.{bid}.feed_forward.experts.down_proj", # llama4
@@ -563,6 +566,7 @@ class TensorNameMap:
"model.layers.{bid}.shared_mlp.output_linear", # granitemoe
"model.layers.{bid}.mlp.shared_mlp.down_proj", # hunyuan
"layers.{bid}.shared_experts.w2", # mistral-large
"backbone.layers.{bid}.mixer.shared_experts.down_proj", # nemotron-h-moe
),
MODEL_TENSOR.FFN_DOWN_CHEXP: (
@@ -706,6 +710,7 @@ class TensorNameMap:
"model.layers.{bid}.mamba.dt_proj", # jamba falcon-h1 granite-hybrid
"model.layers.layers.{bid}.mixer.dt_proj", # plamo2
"model.layers.{bid}.linear_attn.dt_proj", # qwen3next
"backbone.layers.{bid}.mixer.dt", # nemotron-h-moe
),
MODEL_TENSOR.SSM_DT_NORM: (