初始化项目，由ModelHub XC社区提供模型

Model: unsloth/gemma-2-it-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
+unsloth/gemma-2-2b-it.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth/gemma-2-2b-it.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b-it.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+language:
+- en
+library_name: transformers
+license: gemma
+tags:
+- unsloth
+- transformers
+- gemma2
+- gemma
+---
+
+# GGUF uploads
+
+All popular quant variants uploaded.
+
+# Finetune Gemma 2, Llama 3.1, Mistral 2-5x faster with 70% less memory via Unsloth!
+
+Directly quantized 4bit model with `bitsandbytes`.
+
+We have a Google Colab Tesla T4 notebook for **Gemma 2 (2B)** here: https://colab.research.google.com/drive/1weTpKOjBZxZJ5PQ-Ql8i6ptAY2x-FWVA?usp=sharing
+
+We have a Google Colab Tesla T4 notebook for **Gemma 2 (9B)** here: https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+## ✨ Finetune for Free
+
+All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
+
+| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
+|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
+| **Llama 3 (8B)**      | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing)               | 2.4x faster | 58% less |
+| **Gemma 2 (9B)**      | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing)               | 2x faster | 63% less |
+| **Mistral (9B)**    | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing)               | 2.2x faster | 62% less |
+| **Phi 3 (mini)**      | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing)               | 2x faster | 63% less |
+| **TinyLlama**  | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)              | 3.9x faster | 74% less |
+| **CodeLlama (34B)** A100   | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing)              | 1.9x faster | 27% less |
+| **Mistral (7B)** 1xT4  | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
+| **DPO - Zephyr**     | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing)               | 1.9x faster | 19% less |
+
+- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
+- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
+- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google/gemma-2-2b-it",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 256000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

gemma-2-2b-it.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0c160c6f08045def7452353252468bcd9cd63e1fc0ee81bbe6a63f39c7c3df
+size 5235213888

gemma-2-2b-it.q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ed0c497862a20a73613181a1d59282c7385d6132e059005e3fe5f473dafd04
+size 1229829696

gemma-2-2b-it.q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939a1627c931b838376191c3e33be23f26ac01bc285b20f2e26ce9dc8cdbfe95
+size 1461667392

gemma-2-2b-it.q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bf98ab6b26e40f1d69f36cb1202af8b0c1b4e6b50ec2631d576f76cdaac9d6
+size 1708582464

gemma-2-2b-it.q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1f7c16ba0efc3a3083c403429ba285c62c70450b47d55492de682d7d9703fb
+size 1923278400

gemma-2-2b-it.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e92a3052789ab85c220e30df7e3f6316974f0ac8513242554cd74641d402554
+size 2151392832

gemma-2-2b-it.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d844a72d6956f5c2444ad9808ec0b813ef558650b9613eac7ed177e3fb929dca
+size 2784495168