New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48
Browse files
README.md
CHANGED
@@ -18,20 +18,22 @@ This repo contains GGML files for for CPU inference using [llama.cpp](https://gi
|
|
18 |
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ)
|
19 |
* [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
|
20 |
|
21 |
-
## REQUIRES LATEST LLAMA.CPP (May
|
22 |
|
23 |
-
llama.cpp recently made
|
24 |
|
25 |
-
I have
|
26 |
|
27 |
-
|
28 |
|
29 |
## Provided files
|
30 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
31 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
32 |
`WizardLM-7B.GGML.q4_0.bin` | q4_0 | 4bit | 4.2GB | 6GB | 4bit. |
|
33 |
-
`WizardLM-7B.GGML.
|
34 |
-
`WizardLM-7B.GGML.
|
|
|
|
|
35 |
|
36 |
## How to run in `llama.cpp`
|
37 |
|
@@ -51,9 +53,7 @@ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argumen
|
|
51 |
|
52 |
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).
|
53 |
|
54 |
-
Note: at this time text-generation-webui may not support the new llama.cpp quantisation methods
|
55 |
-
|
56 |
-
**Thireus** has written a [great guide on how to update it to the latest llama.cpp code](https://huggingface.co/TheBloke/wizardLM-7B-GGML/discussions/5) to get support for thew newer files quicker.
|
57 |
|
58 |
# Original model info
|
59 |
|
@@ -61,4 +61,4 @@ Overview of Evol-Instruct
|
|
61 |
Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
|
62 |
|
63 |
![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_overall.png)
|
64 |
-
![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_running.png)
|
|
|
18 |
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ)
|
19 |
* [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
|
20 |
|
21 |
+
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
|
22 |
|
23 |
+
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
|
24 |
|
25 |
+
I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.
|
26 |
|
27 |
+
For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
|
28 |
|
29 |
## Provided files
|
30 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
31 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
32 |
`WizardLM-7B.GGML.q4_0.bin` | q4_0 | 4bit | 4.2GB | 6GB | 4bit. |
|
33 |
+
`WizardLM-7B.GGML.q4_1.bin` | q4_0 | 4bit | 4.63GB | 6GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
|
34 |
+
`WizardLM-7B.GGML.q5_0.bin` | q5_0 | 5bit | 4.63GB | 7GB | 5-bit. Higher accuracy, higher resource usage and slower inference.|
|
35 |
+
`WizardLM-7B.GGML.q5_1.bin` | q5_1 | 5bit | 5.0GB | 7GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
|
36 |
+
`WizardLM-7B.GGML.q8_0.bin` | q8_0 | 8bit | 8GB | 10GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
|
37 |
|
38 |
## How to run in `llama.cpp`
|
39 |
|
|
|
53 |
|
54 |
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).
|
55 |
|
56 |
+
Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
|
|
|
|
|
57 |
|
58 |
# Original model info
|
59 |
|
|
|
61 |
Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
|
62 |
|
63 |
![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_overall.png)
|
64 |
+
![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_running.png)
|