TheBloke commited on
Commit
491a53d
1 Parent(s): 3c3ce2c

Initial GGML model commit

Browse files
Files changed (1) hide show
  1. README.md +124 -0
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/Jq4vkcDakD">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
+ # Bigcode's Starcoder GGML
21
+
22
+ These files are GGML format model files for [Bigcode's Starcoder](https://huggingface.co/bigcode/starcoder).
23
+
24
+ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
25
+ * [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
26
+ * [KoboldCpp](https://github.com/LostRuins/koboldcpp)
27
+ * [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
28
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
29
+ * [ctransformers](https://github.com/marella/ctransformers)
30
+
31
+ ## Repositories available
32
+
33
+ * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/starcoder-GPTQ)
34
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/starcoder-GGML)
35
+ * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bigcode/starcoder)
36
+
37
+ <!-- compatibility_ggml start -->
38
+ ## Compatibility
39
+
40
+ ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
41
+
42
+ I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
43
+
44
+ They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.
45
+
46
+ ### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
47
+
48
+ These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
49
+
50
+ They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.
51
+
52
+ ## Explanation of the new k-quant methods
53
+
54
+ The new methods available are:
55
+ * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
56
+ * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
57
+ * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
58
+ * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
59
+ * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
60
+ * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
61
+
62
+ Refer to the Provided Files table below to see what files use which methods, and how.
63
+ <!-- compatibility_ggml end -->
64
+
65
+ ## Provided files
66
+ | Name | Quant method | Bits | Size | Max RAM required | Use case |
67
+ | ---- | ---- | ---- | ---- | ---- | ----- |
68
+ | starcoder.ggmlv3.q4_0.bin | q4_0 | 4 | 10.75 GB | 13.25 GB | Original llama.cpp quant method, 4-bit. |
69
+ | starcoder.ggmlv3.q4_1.bin | q4_1 | 4 | 11.92 GB | 14.42 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
70
+ | starcoder.ggmlv3.q5_0.bin | q5_0 | 5 | 13.09 GB | 15.59 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
71
+ | starcoder.ggmlv3.q5_1.bin | q5_1 | 5 | 14.26 GB | 16.76 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
72
+ | starcoder.ggmlv3.q8_0.bin | q8_0 | 8 | 20.11 GB | 22.61 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
73
+
74
+
75
+ **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
76
+
77
+ ## How to run in `llama.cpp`
78
+
79
+ I use the following command line; adjust for your tastes and needs:
80
+
81
+ ```
82
+ ./main -t 10 -ngl 32 -m starcode.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
83
+ ```
84
+ Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
85
+
86
+ Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
87
+
88
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
89
+
90
+ ## How to run in `text-generation-webui`
91
+
92
+ Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
93
+
94
+ <!-- footer start -->
95
+ ## Discord
96
+
97
+ For further support, and discussions on these models and AI in general, join us at:
98
+
99
+ [TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
100
+
101
+ ## Thanks, and how to contribute.
102
+
103
+ Thanks to the [chirper.ai](https://chirper.ai) team!
104
+
105
+ 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.
106
+
107
+ 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.
108
+
109
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
110
+
111
+ * Patreon: https://patreon.com/TheBlokeAI
112
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
113
+
114
+ **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
115
+
116
+ **Patreon special mentions**: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.
117
+
118
+ Thank you to all my generous patrons and donaters!
119
+
120
+ <!-- footer end -->
121
+
122
+ # Original model card: Bigcode's Starcoder
123
+
124
+ No original model card was provided.