TheBloke commited on
Commit
c637420
1 Parent(s): fc46193

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ license: other
4
+ ---
5
+
6
+ <!-- header start -->
7
+ <div style="width: 100%;">
8
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
9
+ </div>
10
+ <div style="display: flex; justify-content: space-between; width: 100%;">
11
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
12
+ <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
13
+ </div>
14
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
15
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
16
+ </div>
17
+ </div>
18
+ <!-- header end -->
19
+
20
+ # Jon Durin's Airoboros 13B GPT4 GPTQ
21
+
22
+ These files are GPTQ 4bit model files for [Jon Durin's Airoboros 13B GPT4](https://huggingface.co/jondurbin/airoboros-13b-gpt4).
23
+
24
+ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
25
+
26
+ ## Other repositories available
27
+
28
+ * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-13b-gpt4-GPTQ)
29
+ * [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/airoboros-13b-gpt4-GGML)
30
+ * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-13b-gpt4)
31
+
32
+ ## How to easily download and use this model in text-generation-webui
33
+
34
+ ### Downloading the model
35
+
36
+ 1. Click the **Model tab**.
37
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/airoboros-13b-gpt4-GPTQ`.
38
+ 3. Click **Download**.
39
+ 4. Wait until it says it's finished downloading.
40
+ 5. Untick "Autoload model"
41
+ 6. Click the **Refresh** icon next to **Model** in the top left.
42
+
43
+ ### To use with AutoGPTQ (if installed)
44
+
45
+ 1. In the **Model drop-down**: choose the model you just downloaded, `airoboros-13b-gpt4-GPTQ`.
46
+ 2. Under **GPTQ**, tick **AutoGPTQ**.
47
+ 3. Click **Save settings for this model** in the top right.
48
+ 4. Click **Reload the Model** in the top right.
49
+ 5. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
50
+
51
+ ### To use with GPTQ-for-LLaMa
52
+
53
+ 1. In the **Model drop-down**: choose the model you just downloaded, `airoboros-13b-gpt4-GPTQ`.
54
+ 2. If you see an error in the bottom right, ignore it - it's temporary.
55
+ 3. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = 128`, `model_type = Llama`
56
+ 4. Click **Save settings for this model** in the top right.
57
+ 5. Click **Reload the Model** in the top right.
58
+ 6. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
59
+
60
+ ## Provided files
61
+
62
+ **airoboros-13b-gpt4-GPTQ-4bit-128g.no-act.order.safetensors**
63
+
64
+ This will work with all versions of GPTQ-for-LLaMa, and with AutoGPTQ.
65
+
66
+ It was created with
67
+
68
+ * `airoboros-13b-gpt4-GPTQ-4bit-128g.no-act.order.safetensors`
69
+ * Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
70
+ * Works with AutoGPTQ
71
+ * Works with text-generation-webui one-click-installers
72
+ * Parameters: Groupsize = 128. Act Order / desc_act = False.
73
+
74
+ <!-- footer start -->
75
+ ## Discord
76
+
77
+ For further support, and discussions on these models and AI in general, join us at:
78
+
79
+ [TheBloke AI's Discord server](https://discord.gg/UBgz4VXf)
80
+
81
+ ## Thanks, and how to contribute.
82
+
83
+ Thanks to the [chirper.ai](https://chirper.ai) team!
84
+
85
+ I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
86
+
87
+ If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
88
+
89
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
90
+
91
+ * Patreon: https://patreon.com/TheBlokeAI
92
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
93
+
94
+ **Patreon special mentions**: Aemon Algiz; Dmitiry Samsonov; Jonathan Leane; Illia Dulskyi; Khalefa Al-Ahmad; Nikolai Manek; senxiiz; Talal Aujan; vamX; Eugene Pentland; Lone Striker; Luke Pendergrass; Johann-Peter Hartmann.
95
+
96
+ Thank you to all my generous patrons and donaters.
97
+ <!-- footer end -->
98
+
99
+ # Original model card: Jon Durin's Airoboros 13B GPT4