TheBloke commited on
Commit
a5ca5f7
1 Parent(s): ef817b5

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +150 -0
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/theblokeai">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
+ # Panchovix's merge of Guanaco 33B and SuperHOT 8K GPTQ
21
+
22
+ These files are GPTQ 4bit model files for [Panchovix's merge of Guanaco 33B and SuperHOT 8K](https://huggingface.co/Panchovix/Guanaco-33B-SuperHOT-8k).
23
+
24
+ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
25
+
26
+ ## Repositories available
27
+
28
+ * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ)
29
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/none)
30
+ * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Panchovix/Guanaco-33B-SuperHOT-8k)
31
+
32
+ ## How to easily download and use this model in text-generation-webui
33
+
34
+ Please make sure you're using the latest version of text-generation-webui
35
+
36
+ 1. Click the **Model tab**.
37
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ`.
38
+ 3. Click **Download**.
39
+ 4. The model will start downloading. Once it's finished it will say "Done"
40
+ 5. In the top left, click the refresh icon next to **Model**.
41
+ 6. In the **Model** dropdown, choose the model you just downloaded: `Guanaco-33B-SuperHOT-8K-GPTQ`
42
+ 7. The model will automatically load, and is now ready for use!
43
+ 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
44
+ * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
45
+ 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
46
+
47
+ ## How to use this GPTQ model from Python code
48
+
49
+ First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
50
+
51
+ `pip install auto-gptq`
52
+
53
+ Then try the following example code:
54
+
55
+ ```python
56
+ from transformers import AutoTokenizer, pipeline, logging
57
+ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
58
+ import argparse
59
+
60
+ model_name_or_path = "TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ"
61
+ model_basename = "guanaco-33b-superhot-8k-GPTQ-4bit--1g.act.order"
62
+
63
+ use_triton = False
64
+
65
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
66
+
67
+ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
68
+ model_basename=model_basename,
69
+ use_safetensors=True,
70
+ trust_remote_code=False,
71
+ device="cuda:0",
72
+ use_triton=use_triton,
73
+ quantize_config=None)
74
+
75
+ # Note: check the prompt template is correct for this model.
76
+ prompt = "Tell me about AI"
77
+ prompt_template=f'''USER: {prompt}
78
+ ASSISTANT:'''
79
+
80
+ print("\n\n*** Generate:")
81
+
82
+ input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
83
+ output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
84
+ print(tokenizer.decode(output[0]))
85
+
86
+ # Inference can also be done using transformers' pipeline
87
+
88
+ # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
89
+ logging.set_verbosity(logging.CRITICAL)
90
+
91
+ print("*** Pipeline:")
92
+ pipe = pipeline(
93
+ "text-generation",
94
+ model=model,
95
+ tokenizer=tokenizer,
96
+ max_new_tokens=512,
97
+ temperature=0.7,
98
+ top_p=0.95,
99
+ repetition_penalty=1.15
100
+ )
101
+
102
+ print(pipe(prompt_template)[0]['generated_text'])
103
+ ```
104
+
105
+ ## Provided files
106
+
107
+ **guanaco-33b-superhot-8k-GPTQ-4bit--1g.act.order.safetensors**
108
+
109
+ This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
110
+
111
+ It was created without group_size to lower VRAM requirements, and with --act-order (desc_act) to boost inference accuracy as much as possible.
112
+
113
+ * `guanaco-33b-superhot-8k-GPTQ-4bit--1g.act.order.safetensors`
114
+ * Works with AutoGPTQ in CUDA or Triton modes.
115
+ * LLaMa models also work with [ExLlama](https://github.com/turboderp/exllama}, which usually provides much higher performance, and uses less VRAM, than AutoGPTQ.
116
+ * Works with GPTQ-for-LLaMa in CUDA mode. May have issues with GPTQ-for-LLaMa Triton mode.
117
+ * Works with text-generation-webui, including one-click-installers.
118
+ * Parameters: Groupsize = -1. Act Order / desc_act = True.
119
+
120
+ <!-- footer start -->
121
+ ## Discord
122
+
123
+ For further support, and discussions on these models and AI in general, join us at:
124
+
125
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
126
+
127
+ ## Thanks, and how to contribute.
128
+
129
+ Thanks to the [chirper.ai](https://chirper.ai) team!
130
+
131
+ 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.
132
+
133
+ 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.
134
+
135
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
136
+
137
+ * Patreon: https://patreon.com/TheBlokeAI
138
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
139
+
140
+ **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
141
+
142
+ **Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire.
143
+
144
+ Thank you to all my generous patrons and donaters!
145
+
146
+ <!-- footer end -->
147
+
148
+ # Original model card: Panchovix's merge of Guanaco 33B and SuperHOT 8K
149
+
150
+ [guanaco-33b](https://huggingface.co/timdettmers/guanaco-33b-merged) merged with kaiokendev's [33b SuperHOT 8k LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test), without quant. (Full FP16 model)