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

llama : support upcoming Qwen2 (#5037)

Browse source
This commit is contained in:
Shijie 2024-01-19 19:53:13 +08:00 • committed by GitHub
parent de9a147df1
commit 9b75cb2b3c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 211 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert-hf-to-gguf.py
View file

@ -189,6 +189,8 @@ class Model:
return StableLMModel
if model_architecture == "QWenLMHeadModel":
return QwenModel
if model_architecture == "Qwen2ForCausalLM":
return Model
if model_architecture == "MixtralForCausalLM":
return MixtralModel
if model_architecture == "GPT2LMHeadModel":
@ -236,6 +238,8 @@ class Model:
return gguf.MODEL_ARCH.STABLELM
if arch == "QWenLMHeadModel":
return gguf.MODEL_ARCH.QWEN
if arch == "Qwen2ForCausalLM":
return gguf.MODEL_ARCH.QWEN2
if arch == "MixtralForCausalLM":
return gguf.MODEL_ARCH.LLAMA
if arch == "GPT2LMHeadModel":