初始化项目，由ModelHub XC社区提供模型

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

.gitattributes

@@ -0,0 +1,48 @@
+*.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-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+quark-135m-f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+- instruct
+- small-model
+- 135m
+- quark
+- llama-cpp
+- gguf-my-repo
+base_model: ThingAI/Quark-135m
+---
+
+# usermma/Quark-135m-GGUF
+This model was converted to GGUF format from [`ThingAI/Quark-135m`](https://huggingface.co/ThingAI/Quark-135m) 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) 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-GGUF --hf-file quark-135m-q2_k.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo usermma/Quark-135m-GGUF --hf-file quark-135m-q2_k.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-GGUF --hf-file quark-135m-q2_k.gguf -p "The meaning to life and the universe is"
+```
+or
+```
+./llama-server --hf-repo usermma/Quark-135m-GGUF --hf-file quark-135m-q2_k.gguf -c 2048
+```

quark-135m-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccab17c9908b94818ae12f1aceedd4e953a7b995e5d630811cc9337f6c671cd7
+size 271076064

quark-135m-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca4287b747d98e18a361ec556eb645d4574b49d8f9e47b9b15d2f9c2c89e51f
+size 88391904

quark-135m-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfb32880ef422f667b04f6d7b627ea483317c6cddb54800e8b890020642176b
+size 97723104

quark-135m-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74108805d23e0c8077e092afe3ad68f9b1d72f1d7a5e66112fa7c43b63a5c00
+size 93700320

quark-135m-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed64db35a083c2a01b31e10934a82a98b0efa7fe09264a52b8bfcf496ba3d74
+size 88391904

quark-135m-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316e0bfec2ac11a8c586e5b817169982a962eb3e98f01502ca74bd17809b40a0
+size 91917024

quark-135m-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a074309947bafa704fcb51a9a8f90eafc0b30beb8e06cd63eb8a6d2528adc21
+size 105644256

quark-135m-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cf53989178a73b9206beb44b83c1bab84499c979c0f4d9c3a30e3f2bf44452
+size 102229728

quark-135m-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f269b6193d056179657d230aa1e3a2aed4d0b95e62347f14eb422dd6c9ea9bd2
+size 105188064

quark-135m-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c87a6fa01af57d11dd603cc3c2457c651c75ba0b9e773667991b72b914f2ee9
+size 112293600

quark-135m-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8164411944a8d9fd008fefcc7dd73725a3fbd45da75ed8ac1a9ae0b7f740f5
+size 110164704

quark-135m-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1579ab10096d78555e3784cc918ddbee34fae8ab3e5ae915653e3e8f66651fa
+size 138573024

quark-135m-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20566a601a559a094c5d3f560a6622c90b744fda3bf4201d9a9e3cd0816130d2
+size 145001184