初始化项目，由ModelHub XC社区提供模型

Model: usermma/Quark-135m-Bilingual-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,50 @@
+*.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
+quark-135m-bilingual-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-f16.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-f32.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-bilingual-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- it
+- en
+license: apache-2.0
+tags:
+- text-generation
+- causal-lm
+- bilingual
+- italian
+- english
+- small-language-model
+- trained-from-scratch
+- quark
+- llama-cpp
+- gguf-my-repo
+library_name: transformers
+pipeline_tag: text-generation
+base_model: ThingAI/Quark-135m-Bilingual
+model-index:
+- name: Quark-135m-Bilingual
+  results: []
+---
+
+# usermma/Quark-135m-Bilingual-GGUF
+This model was converted to GGUF format from [`ThingAI/Quark-135m-Bilingual`](https://huggingface.co/ThingAI/Quark-135m-Bilingual) 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/ThingAI/Quark-135m-Bilingual) 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 usermma/Quark-135m-Bilingual-GGUF --hf-file quark-135m-bilingual-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo usermma/Quark-135m-Bilingual-GGUF --hf-file quark-135m-bilingual-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 usermma/Quark-135m-Bilingual-GGUF --hf-file quark-135m-bilingual-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+or
+```
+./llama-server --hf-repo usermma/Quark-135m-Bilingual-GGUF --hf-file quark-135m-bilingual-q4_k_m.gguf -c 2048
+```

quark-135m-bilingual-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2151617b911d2da5e26342a479f1b11a02d8a3fbe938338b6fc827da7bfa4743
+size 290484000

quark-135m-bilingual-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc6d71eb6ca67c078113b6c3adfc858be22a217198796dfb28eb5040fdc01e9
+size 290484000

quark-135m-bilingual-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5837cd5b656bb6243d8c274a7c055290cb6a385d00ba51651f0ed9c4c5756d
+size 578319264

quark-135m-bilingual-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315b4f94663c60cd4198702d595ef5d51c274a2dab7eb93d77411b772af944b7
+size 98951968

quark-135m-bilingual-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154ebc43891bbaa4ff53c086ac2a49a711d9754889c7565bf26c28023f674efc
+size 108283168

quark-135m-bilingual-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0171f4c9ee3abed4ccc83d2dd79250081f4c6dce73cd409b1453d8e8ea24613d
+size 104260384

quark-135m-bilingual-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58bfe7eee753f84bbee87d0f2aa96007f587126293d212e1e6a830d8c961e3f1
+size 98951968

quark-135m-bilingual-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274e8a75da7e070252191306aaea30b5e125782e4966d8f604b7ea9996ed28a3
+size 102477088

quark-135m-bilingual-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d589c0f1e4b7dc72da5374649c8d6bd3b3b60d2aa5115b25838ffefc5a49d8ac
+size 116204320

quark-135m-bilingual-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52119c6b46a3ab5f18a9b3136f264b56e37ef654c7b06aaaa970dc0fd8abb15
+size 112789792

quark-135m-bilingual-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59c895f86060953a3606578ac7b6b99c060251723952621987dbf6798d176e7
+size 115748128

quark-135m-bilingual-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a354a5178a82cdae8371683364f898c8a5fa83ee9200829273f29fd65766641
+size 122853664

quark-135m-bilingual-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ee8dfda894a326f298a83a8d03cd1d037188951f0a5faf9ec4e6be4b62964f
+size 120724768

quark-135m-bilingual-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b47297fb2fc83948082c7e37c9b433992f56669e5b7ec19a2f90aae5ebefab4
+size 149133088

quark-135m-bilingual-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28d84dde3ff3dc33eeea4de317a450654f6cb7eb9c19c8890844af7cdddb2e6
+size 155561248