Hugging Face's logo

RichardErkhov
/
unsloth_-_gemma-2-2b-gguf

GGUF
Inference Endpoints
Model card Files Community
RichardErkhov commited on
Commit
f548727
•
1 Parent(s): dd6cdc2

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ gemma-2-2b - GGUF
11
+ - Model creator: https://huggingface.co/unsloth/
12
+ - Original model: https://huggingface.co/unsloth/gemma-2-2b/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [gemma-2-2b.Q2_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q2_K.gguf) | Q2_K | 1.15GB |
18
+ | [gemma-2-2b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_XS.gguf) | IQ3_XS | 1.22GB |
19
+ | [gemma-2-2b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_S.gguf) | IQ3_S | 1.27GB |
20
+ | [gemma-2-2b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_S.gguf) | Q3_K_S | 1.27GB |
21
+ | [gemma-2-2b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ3_M.gguf) | IQ3_M | 1.3GB |
22
+ | [gemma-2-2b.Q3_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K.gguf) | Q3_K | 1.36GB |
23
+ | [gemma-2-2b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_M.gguf) | Q3_K_M | 1.36GB |
24
+ | [gemma-2-2b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q3_K_L.gguf) | Q3_K_L | 1.44GB |
25
+ | [gemma-2-2b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_XS.gguf) | IQ4_XS | 1.47GB |
26
+ | [gemma-2-2b.Q4_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_0.gguf) | Q4_0 | 1.52GB |
27
+ | [gemma-2-2b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.IQ4_NL.gguf) | IQ4_NL | 1.53GB |
28
+ | [gemma-2-2b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_S.gguf) | Q4_K_S | 1.53GB |
29
+ | [gemma-2-2b.Q4_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K.gguf) | Q4_K | 1.59GB |
30
+ | [gemma-2-2b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_K_M.gguf) | Q4_K_M | 1.59GB |
31
+ | [gemma-2-2b.Q4_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q4_1.gguf) | Q4_1 | 1.64GB |
32
+ | [gemma-2-2b.Q5_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_0.gguf) | Q5_0 | 1.75GB |
33
+ | [gemma-2-2b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_S.gguf) | Q5_K_S | 1.75GB |
34
+ | [gemma-2-2b.Q5_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K.gguf) | Q5_K | 1.79GB |
35
+ | [gemma-2-2b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_K_M.gguf) | Q5_K_M | 1.79GB |
36
+ | [gemma-2-2b.Q5_1.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q5_1.gguf) | Q5_1 | 1.87GB |
37
+ | [gemma-2-2b.Q6_K.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q6_K.gguf) | Q6_K | 2.0GB |
38
+ | [gemma-2-2b.Q8_0.gguf](https://huggingface.co/RichardErkhov/unsloth_-_gemma-2-2b-gguf/blob/main/gemma-2-2b.Q8_0.gguf) | Q8_0 | 2.59GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ language:
46
+ - en
47
+ library_name: transformers
48
+ license: gemma
49
+ tags:
50
+ - unsloth
51
+ - transformers
52
+ - gemma2
53
+ - gemma
54
+ ---
55
+
56
+ ## Reminder to use the dev version Transformers:
57
+ `pip install git+https://github.com/huggingface/transformers.git`
58
+
59
+ # Finetune Gemma 2, Llama 3.1, Mistral 2-5x faster with 70% less memory via Unsloth!
60
+
61
+ Directly quantized 4bit model with `bitsandbytes`.
62
+
63
+ We have a Google Colab Tesla T4 notebook for **Gemma 2 (2B)** here: https://colab.research.google.com/drive/1weTpKOjBZxZJ5PQ-Ql8i6ptAY2x-FWVA?usp=sharing
64
+
65
+ We have a Google Colab Tesla T4 notebook for **Gemma 2 (9B)** here: https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing
66
+
67
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
68
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
69
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
70
+
71
+ ## ✨ Finetune for Free
72
+
73
+ 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.
74
+
75
+ | Unsloth supports | Free Notebooks | Performance | Memory use |
76
+ |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
77
+ | **Llama 3 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2.4x faster | 58% less |
78
+ | **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2x faster | 63% less |
79
+ | **Mistral (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
80
+ | **Phi 3 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 63% less |
81
+ | **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
82
+ | **CodeLlama (34B)** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less |
83
+ | **Mistral (7B)** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
84
+ | **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
85
+
86
+ - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
87
+ - 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.
88
+ - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
89
+