初始化项目，由ModelHub XC社区提供模型

Model: hoangton/gemma-2b-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+gemma-2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+library_name: transformers
+tags: []
+extra_gated_heading: "Access Gemma on Hugging Face"
+extra_gated_prompt: "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately."
+extra_gated_button_content: "Acknowledge license"
+license: other
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+---
+
+# Gemma-2B GGUF
+
+This is a quantized version of the [google/gemma-2b](https://huggingface.co/google/gemma-2b) model using [llama.cpp](https://github.com/ggerganov/llama.cpp).
+
+This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). 
+
+**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
+
+**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
+
+## ⚡ Quants
+
+* `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
+* `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
+* `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
+* `q3_k_s`: Uses Q3_K for all tensors
+* `q4_0`: Original quant method, 4-bit.
+* `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
+* `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
+* `q4_k_s`: Uses Q4_K for all tensors
+* `q5_0`: Higher accuracy, higher resource usage and slower inference.
+* `q5_1`: Even higher accuracy, resource usage and slower inference.
+* `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
+* `q5_k_s`:  Uses Q5_K for all tensors
+* `q6_k`: Uses Q8_K for all tensors
+* `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
+
+## 💻 Usage
+
+This model can be used with the latest version of llama.cpp and LM Studio >0.2.16.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

gemma-2b.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e987bf77ffff2d873e5b06310dfe8847f03178cdd27812c84f95d8c5c488c59
+size 899875936

gemma-2b.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2a686bdf24e52055ee55b323ddd2a077d99bdb370db1d114d96415227e67a2
+size 1260790880

gemma-2b.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3711a880951eba56dc201e0160154cff115f9a96cf0b56a8041d7136daa55f2
+size 1179001952

gemma-2b.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ccf460c7491354923e8be50978b962e3c8e742df0d7e9466578dccf95bfdbd
+size 1083180128

gemma-2b.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acaf847c0c4b51888f4ba9362e031216a07629c1cbf30d5db89d460719e810e
+size 1416021088

gemma-2b.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a58d042d6eda5436f47c4ca125cba401c7b5ec67ec4194bbbfaa473fa76295
+size 1572652128

gemma-2b.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d50c21ef7847926204ad9b3007127d9a2722188cfd240ce7f9f7f041aa71a5
+size 1495094368

gemma-2b.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588b26a208ef99d7cefa7137ef074257e51250c7096cecad51349fdc941647ac
+size 1424671840

gemma-2b.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4164b683fddc18bdc78d355f49264239a045ad5a54f8deb5e4b1d07d3498d13a
+size 1729283168

gemma-2b.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97498ad926467c426d2ee87da99b54afd840e5dec6b65fa3b1c9de2f7f5d6b5a
+size 1885914208

gemma-2b.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226f65d1a2463a35baad4c94af0d5deb4df29ea2a15c208de00be80989f508eb
+size 1770017888

gemma-2b.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee20c0c2046d06ab9c4447fa3abaa880bfbaa1816de483ded5f1a060edfbf9be
+size 1729283168

gemma-2b.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f42096801c3c6b1537e60f9416abfd103d5c4a37312ac437170485d61a4375
+size 2062124128

gemma-2b.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef61ca7b06ea0afba21ee65922e066f7ae8e1a35bb151cf41846251bfb1a5a8
+size 2669069408