Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 17:24:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

add more variants

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-17 09:12:19 +02:00
parent 584b4f93c6
commit 6e97dc0518
4 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/gemma.py
+4 -4
View File
@@ -123,7 +123,7 @@ class Gemma2Model(TextModel):
@ModelBase.register("Gemma3ForCausalLM", "Gemma3ForConditionalGeneration")
# [TAG_HF_EXAMPLE_GATED] google/gemma-3-4b-it is gated
@ModelBase.example("trl-internal-testing/tiny-Gemma3ForConditionalGeneration")
@ModelBase.example("trl-internal-testing/tiny-Gemma3ForConditionalGeneration", "hf-tiny-v2/tiny-random-Gemma3ForCausalLM")
class Gemma3Model(TextModel):
model_arch = gguf.MODEL_ARCH.GEMMA3
@@ -629,7 +629,7 @@ class Gemma3NModel(Gemma3Model):
@ModelBase.register("Gemma4ForConditionalGeneration", "Gemma4ForCausalLM")
@ModelBase.example("google/gemma-4-31B-it", "google/gemma-4-26B-A4B-it")
@ModelBase.example("google/gemma-4-31B-it", "google/gemma-4-26B-A4B-it", "google/gemma-4-E2B-it")
class Gemma4Model(Gemma3Model):
model_arch = gguf.MODEL_ARCH.GEMMA4
@@ -831,7 +831,7 @@ class Gemma4UnifiedModel(Gemma4Model):
@ModelBase.register("Gemma4AssistantForCausalLM", "Gemma4UnifiedAssistantForCausalLM")
@ModelBase.example("google/gemma-4-31B-it-assistant")
@ModelBase.example("google/gemma-4-31B-it-assistant", "google/gemma-4-26B-A4B-it-assistant", "google/gemma-4-E2B-it-assistant")
class Gemma4AssistantModel(Gemma4Model):
model_arch = gguf.MODEL_ARCH.GEMMA4_ASSISTANT
@@ -852,7 +852,7 @@ class Gemma4AssistantModel(Gemma4Model):
@ModelBase.register("Gemma4ForConditionalGeneration")
@ModelBase.example("google/gemma-4-31B-it")
@ModelBase.example("google/gemma-4-31B-it", "google/gemma-4-26B-A4B-it", "google/gemma-4-E2B-it")
class Gemma4VisionAudioModel(MmprojModel):
has_audio_encoder = True
has_vision_encoder = True
conversion/llama.py
+1 -1
View File
@@ -29,7 +29,7 @@ from .base import ModelBase, TextModel, gguf, logger
"IQuestCoderForCausalLM",
"LlamaModel")
# [TAG_HF_EXAMPLE_GATED] meta-llama/Llama-3.2-1B-Instruct is gated
@ModelBase.example("unsloth/Llama-3.2-1B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3")
@ModelBase.example("unsloth/Llama-3.2-1B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3", "mistralai/Mixtral-8x7B-Instruct-v0.1")
class LlamaModel(TextModel):
model_arch = gguf.MODEL_ARCH.LLAMA
undo_permute = True
conversion/mistral3.py
+1 -1
View File
@@ -15,7 +15,7 @@ from .llama import LlamaModel
"Mistral3ForConditionalGeneration",
"Ministral3ForCausalLM",
)
@ModelBase.example("mistralai/Mistral-Small-3.1-24B-Instruct-2503")
@ModelBase.example("mistralai/Mistral-Small-3.1-24B-Instruct-2503", "hf-tiny-v2/tiny-random-Ministral3ForCausalLM")
class Mistral3Model(TextModel):
class Ministral3Model(LlamaModel):
model_arch = gguf.MODEL_ARCH.MISTRAL3
conversion/qwen3vl.py
+1 -1
View File
@@ -14,7 +14,7 @@ from .qwenvl import Qwen25AudioModel
@ModelBase.register("Qwen3VLForConditionalGeneration", "Qwen3VLMoeForConditionalGeneration", "Qwen3_5ForConditionalGeneration", "Qwen3_5MoeForConditionalGeneration")
@ModelBase.example("Qwen/Qwen3-VL-4B-Instruct", "Qwen/Qwen3-VL-30B-A3B-Instruct")
@ModelBase.example("Qwen/Qwen3-VL-4B-Instruct", "Qwen/Qwen3-VL-30B-A3B-Instruct", "Qwen/Qwen3.5-9B", "Qwen/Qwen3.5-35B-A3B")
class Qwen3VLVisionModel(MmprojModel):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)