预训练之后的模型和llama-2-7b-hf合并,量化

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+ggml-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-model-q6_K.bin filter=lfs diff=lfs merge=lfs -text

ggml-model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4578d0c031bf079018b1e6571dc78ebef7a5f8415a58692869a965c8c359fc60
+size 13860294144

ggml-model-q6_K.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c973ebd175308285f216ff7202dd1c3b7f985faf32904f69e3ebc0d73585db
+size 5686251040

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5fdd282e77dc26aa62a80cdf7ba8d5b2c4ddc280cef5b07b60c4b8d3cba6d3
+oid sha256:7ab01965ad9b9233852bc8e5cdf125d21e70ce1edc00100c1d564e4054e753f9
 size 10167475414

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7578414c186e0b8b39ef9805362c1f402ac9a9910a7213b0ac042fbb7f44e9
+oid sha256:956b0e223bb776d555b2adc493a7379077ad9c304d764a28c6b9be16435d4006
 size 3691156371

special_tokens_map.json

@@ -13,7 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,