Upload 7 files

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ERNIE-4.5-0.3B-PT-F16.gguf filter=lfs diff=lfs merge=lfs -text
+ernie-4.5-0.3b-pt-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+ernie-4.5-0.3b-pt-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+ERNIE-4.5-0.3B-PT-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ernie-4.5-0.3b-pt-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

ERNIE-4.5-0.3B-PT-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee25587d9f4843661bf61eb064cd67b7915a73c1317fb833952de9754eada01
+size 723954720

ERNIE-4.5-0.3B-PT-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bdd700c4b088c07d600d6c1e4cb6fb9d1a63698b7d1546e24c2a93aac5ed7b
+size 268662240

README.md

@@ -1,3 +1,57 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+- zh
+pipeline_tag: text-generation
+tags:
+- ERNIE4.5
+- llama-cpp
+- gguf-my-repo
+library_name: transformers
+base_model: baidu/ERNIE-4.5-0.3B-PT
+---
+
+# dengcao/ERNIE-4.5-0.3B-PT-GGUF
+This model was converted to GGUF format from [`baidu/ERNIE-4.5-0.3B-PT`](https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo dengcao/ERNIE-4.5-0.3B-PT-GGUF --hf-file ernie-4.5-0.3b-pt-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo dengcao/ERNIE-4.5-0.3B-PT-GGUF --hf-file ernie-4.5-0.3b-pt-q4_k_m.gguf -c 2048
+```
+
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo dengcao/ERNIE-4.5-0.3B-PT-GGUF --hf-file ernie-4.5-0.3b-pt-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo dengcao/ERNIE-4.5-0.3B-PT-GGUF --hf-file ernie-4.5-0.3b-pt-q4_k_m.gguf -c 2048
+```

ernie-4.5-0.3b-pt-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65e10d5e6c215cd13121ea7d9c096d5f4850f7b19c3997466bf1744279465d9
+size 212515872

ernie-4.5-0.3b-pt-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29ced3fdde116b9b626345a156c2638402090bd267af8c8f9b6d38888997557
+size 240645152

ernie-4.5-0.3b-pt-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d492d453e980e6b30b7a3dfb6062a8cafdd90cf583a411135f6f298f2fe5623
+size 385788960

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text