This repository has been archived by the owner on Jun 22, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 65
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add Mixtral 8x7B Q3 and Q6 configurations (#54)
* Mixtral * Added 3 bit quantized version of Mixtral, updated licenses * Update mixtral-Q3.yaml Signed-off-by: lunamidori5 <[email protected]> * Update mixtral-Q6.yaml Signed-off-by: lunamidori5 <[email protected]> --------- Signed-off-by: lunamidori5 <[email protected]> Co-authored-by: root <[email protected]> Co-authored-by: lunamidori5 <[email protected]>
- Loading branch information
3 people
authored
Jan 8, 2024
1 parent
97e7900
commit 46546f8
Showing
2 changed files
with
84 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| name: "mixtral-8x7B-Q3_K_M" | ||
|
|
||
| description: | | ||
| This is a mixtral model | ||
| license: "https://www.apache.org/licenses/LICENSE-2.0" | ||
| urls: | ||
| - https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF | ||
|
|
||
| config_file: | | ||
| name: mixtral-8x7B-Q3_K_M | ||
| context_size: 4096 | ||
| f16: true | ||
| mmap: true | ||
| #gpu_layers: 90 # uncomment to offload all layers to GPU | ||
| threads: 8 | ||
| parameters: | ||
| model: mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf | ||
| temperature: 0.2 | ||
| top_k: 40 | ||
| top_p: 0.95 | ||
| frequency_penalty: 1.1 | ||
| batch: 512 | ||
| tfz: 1.0 | ||
| template: | ||
| chat: mixtral-chat | ||
| completion: mixtral-completion | ||
| stopwords: | ||
| - <|im_end|> | ||
| prompt_templates: | ||
| - name: "mixtral-chat" | ||
| content: | | ||
| [INST] {{.Input}} [/INST] | ||
| - name: "mixtral-completion" | ||
| content: | | ||
| [INST] {{.Input}} [/INST] | ||
| files: | ||
| - filename: "mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf" | ||
| sha256: "bd2e1499e68195f1a6ff151e6fa5c6632acc150b80cca4a3772cbb7ca59d44cd" | ||
| uri: "https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| name: "mixtral-8x7B-Q6_K" | ||
|
|
||
| description: | | ||
| This is a mixtral model | ||
| license: "https://www.apache.org/licenses/LICENSE-2.0" | ||
| urls: | ||
| - https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF | ||
|
|
||
| config_file: | | ||
| name: mixtral-8x7B-Q6_K | ||
| context_size: 4096 | ||
| f16: true | ||
| mmap: true | ||
| gpu_layers: 90 # Comment out to disable offloading to GPU | ||
| threads: 10 | ||
| parameters: | ||
| model: mixtral-8x7b-instruct-v0.1.Q6_K.gguf | ||
| temperature: 0.2 | ||
| top_k: 40 | ||
| top_p: 0.95 | ||
| frequency_penalty: 1.1 | ||
| batch: 512 | ||
| tfz: 1.0 | ||
| template: | ||
| chat: mixtral-chat | ||
| completion: mixtral-completion | ||
| stopwords: | ||
| - <|im_end|> | ||
| prompt_templates: | ||
| - name: "mixtral-chat" | ||
| content: | | ||
| [INST] {{.Input}} [/INST] | ||
| - name: "mixtral-completion" | ||
| content: | | ||
| [INST] {{.Input}} [/INST] | ||
| files: | ||
| - filename: "mixtral-8x7b-instruct-v0.1.Q6_K.gguf" | ||
| sha256: "56638f9853b8fff80ac1fd4a91434a1c15c21d4c910811c5458df9ef092615fd" | ||
| uri: "https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/mixtral-8x7b-instruct-v0.1.Q6_K.gguf" |