Olivier DEBAUCHE
7151af023f
Add support for OpenCodeInterpreter models ( #1165 )
...
* Add support for OpenCodeInterpreter models
Add support for OpenCodeInterpreter DS 6.7B
Add support for OpenCodeInterpreter DS 33B
Add support for OpenCodeInterpreter CL-7B
Add support for OpenCodeInterpreter CL-13B
Add support for OpenCodeInterpreter CL-70B
* Update README.md
Add support for OpenCodeInterpreter DS 6.7B
Add support for OpenCodeInterpreter DS 33B
Add support for OpenCodeInterpreter CL-7B
Add support for OpenCodeInterpreter CL-13B
Add support for OpenCodeInterpreter CL-70B
* Update README.md
2024-02-26 20:19:22 -05:00
Olivier DEBAUCHE
26bf8a3c29
Update Gemma Models ( #1158 )
...
* Update Gemma Models
Update Gemma 2B & 7B
Add support for Gemma 2B-Instruct
Add support for Gemma 7B-Instruct
* Update Gemma Models
Update Gemma 2B & 7B
Add support for Gemma 2B-Instruct
Add support for Gemma 7B-Instruct
2024-02-25 15:57:30 -05:00
Olivier DEBAUCHE
d1ce38450f
Add support for BioMistral, Nous-Hermes-2-Mistral and Nous-Hermes-2-Mixtral ( #1156 )
...
* Update models.json
Add support for BioMistral 7B
Add support for Nous-Hermes-2-Mistral-7B-DPO
Add support for Nous-Hermes-2-Mixtral-8x7B-DPO
Add support for Nous-Hermes-2-Mixtral-8x7B-SFT
* Update README.md
Add support for BioMistral 7B
Add support for Nous-Hermes-2-Mistral-7B-DPO
Add support for Nous-Hermes-2-Mixtral-8x7B-DPO
Add support for Nous-Hermes-2-Mixtral-8x7B-SFT
2024-02-25 14:49:43 -05:00
Olivier DEBAUCHE
b5b35fc11e
Models update ( #1154 )
...
* Update models.json
Add support for Gemma 2B and 7B
* Update models.json
Add support for LLama pro
* Update models.json
Add support for TinyLlama
* Update models.json
Update Medicine LLM
* Update README.md
* Update serge.env
Bump version of LLama cpp to support Gemma Model
2024-02-24 00:55:16 -05:00
Olivier DEBAUCHE
fcfb579e6a
Update README.md ( #1113 )
2024-02-05 19:23:53 -05:00
morpheus2448
1a0a70be46
Update documentation, Add titles to sections ( #1054 )
...
* Add support for Podman
* Adding tooltips to chat params top bar
* Delete podman-compose.dev.yml
* Add :z labels to mounts for podman compatibility
* Making things prettier
2024-01-13 10:14:21 -05:00
Olivier DEBAUCHE
3d4e5c5b12
Add support for Phi 2 ( #1030 )
...
* Update README.md
* Update models.json
* Update README.md
Add support for Phi 2
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-01-03 19:19:59 -05:00
Olivier DEBAUCHE
2cae77830b
Update README.md ( #1029 )
2024-01-03 19:11:52 -05:00
Olivier DEBAUCHE
d50c93cbfc
Add Mixtral 2.7, MedicineLLM, MistralLite, and Notux ( #1026 )
...
* Update models.json
Update from Mixtral 8x7b-Dolphin 2.5 to Mixtral 8x7b - Dolphin 2.7
* Update README.md
Add Medicine-LLM13B
* Update models.json
Add Medicine LLM 13B
* Update models.json
Add MistralLite-7B
* Update README.md
Add support for MistralLite-7B
Add support for Notux 8x7B
* Update models.json
Add support for MistralLite-7b
Add support for Notux 8x7B v1
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-01-02 22:21:05 -05:00
Juan Calderon-Perez
10626ce6a2
Update README.md
2024-01-01 23:08:12 -05:00
Olivier DEBAUCHE
98bdb9f8b0
Add support for Mixtral 8x7B-Dolphin 2.5 and WizardLM ( #997 )
...
* Add support for Mixtral 8x7B - Dolphin 2.5
* Add Support for WizardLM
* Add new LLMs
- Add support for Mixtral 8x7B - Dolphin 2.5
- Add support for WizardLM
- Update README.md
* Remove support of WizardLM 7B -UNCENSORED
* Remove support of WizardLM 7B -UNCENSORED
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-19 08:27:10 -05:00
Olivier DEBAUCHE
b27b8064b1
Update OpenChat v3.5, Add Medalpaca 13B ( #983 )
...
* Update models.json
* Update OpenChat v3.5 to OpenChat v3.5-1012
* Update README.md
Update from OpenChat v3.5 to OpenChat v3.5-1012
* Update models.json
Add Phi-2
* Update README.md
Add Phi 2
* Update models.json
* Update README.md
* Update models.json
Add Medalpaca 13B
* Update README.md
Add Medalpaca 13B
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-17 13:51:10 -05:00
Olivier DEBAUCHE
41042698f0
Update Neural Chat, Mistral models and add Code 13B, 33B, Meditron 7B-Chat, Mixtral 8x7B LLMs ( #976 )
...
* Update Neural-Chat Modem
Update Neural Chat from v3.2 to v3.3
* Update Neural Chat model
Update Neural Chat from v3.2 to v3.3
* Add Meditron 7B -Chet model
Add Meditron 7B - Chat
* Add Code 13B and 33B models
Add Code 13B
Add Code 33B
* Add Models Code 13B and Code 33B
* Update Mistral 7B-Instruct
Update Mistral 7B Instruction from v0.1 to v0.2
* Add Mixtral LLMs
Add Mixtral 8x7B v0.1
Add Mixtral 8x7B-Instruct v0.1
* Update README.md
Add Mixtral 8x7B v0.1
Add Mixtral 8x7B Instruct v0.1
Upgrade Mistral 7B from v0.1 to v0.2
* Update README.md
tiny update
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-15 08:05:52 -05:00
Olivier DEBAUCHE
71375c4af9
Add Vicuna 33B-Coder and LLaMA-2 7B-Coder models ( #965 )
...
* Update README.md
Add Vicuna 33B-Coder
Add LLaMA-2 7B-Coder
* Add Vicuna 33B-Coder and LLaMA-2 7B-Coder
Add Vicuna 33B-Coder
Add LLaMA-2 7B-Coder
2023-12-09 18:19:40 -05:00
Olivier DEBAUCHE
9dae3f4e13
Add Vicuna 33B model ( #964 )
2023-12-09 17:37:17 -05:00
Olivier DEBAUCHE
59b7fe76e6
Updates to CodeLLaMA models ( #963 )
...
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-09 17:23:57 -05:00
Olivier DEBAUCHE
9bcab1297c
Add Python-Code 13B and 33B ( #960 )
...
* Add Python-Code 13B and 33B
* Add Python-Code 13B and 33B
* Update README.md
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-08 18:19:50 -05:00
Juan Calderon-Perez
51ef0b3b61
Add Zephyr 3B ( #959 )
2023-12-08 09:24:06 -05:00
Juan Calderon-Perez
e2c2cebf7d
Update README.md
2023-12-07 00:38:40 -05:00
Olivier DEBAUCHE
e5be21ccf2
Fix file sizes of LLM's ( #945 )
...
* Update models.json
Reorganization of models.json file
* Update models.json
Add support for SlimOrca 13B
* Update models.json
Falcon 7B file size bugfix
* Update models.json
Falcon 7B filesize updated
* Update models.json
Falcon 7B fix
* Update models.json
Vicuna-13B fix
* Update models.json
SlimOrca bugfix
* Update models.json
Model filesize updated
Thx Gaby for the snippet :)
* Update models.json
Add support for Llama-2-70B-OASST
* Update README.md
Add support for Llama-2-70B-OASST
* Update README.md
tiny correctoin
* Update models.json
Add Support for LLaMA 2 7B, 13B, 70B
* Update README.md
Add support for LLaMA 2 7B, 13B, 70B
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-05 20:29:13 -05:00
Olivier DEBAUCHE
dc6136dd1f
Add support for Notus LLM ( #937 )
2023-12-03 18:17:37 -05:00
Olivier DEBAUCHE
c23402153d
Add support for Alfred LLM ( #936 )
...
* Update models.json
Add support of Alfred 40B (supporting 5 languages)
* Update README.md
Add support of Alfred 40B (supporting 5 languages)
2023-12-03 13:11:17 -05:00
Olivier DEBAUCHE
bc10144ed5
Upgrade for Neural-Chat from v3.1 to v3.2 ( #935 )
...
* Update models.json
Ugrade NeuralChat from v3.1 to v3.2
* Update README.md
Upgrade Neural-Chat from v3.1 to v3..2
2023-12-03 12:28:35 -05:00
Juan Calderon-Perez
912a38da7d
Cleanup LLM names ( #933 )
2023-12-02 17:05:34 -05:00
Juan Calderon-Perez
045ba1c34b
Update README.md
2023-12-02 10:47:55 -05:00
Olivier DEBAUCHE
d1ef2b5416
Update README.md ( #931 )
...
add missing "cd serge"
2023-12-02 10:46:20 -05:00
Olivier DEBAUCHE
ab8e376bc3
Add support for Med42 and PsyMedRP ( #929 )
2023-12-02 09:38:29 -05:00
Olivier DEBAUCHE
9fabef6db1
Add support for Neural-Chat, OpenChat, Orca 2, and OpenLLaMa v2, Starling LM ( #926 )
...
* Update models.json
Add support of Orca-2
Add support Open LLaMa
Add Neural-Chat
* Update README.md
* Update README.md
add Falcon 180B and Falcon 180B-Chat
* Update README.md
Add support of OpenChat 3.5
* Update models.json
bugfix
* Update README.md
Typo fix
* Update models.json
Add support of Falcon 180B, Falcon 180B-Chat
Add support of OpenChat 3.5
* Update README.md
bugfix
* Update models.json
neural bugfix
* Update models.json
remove Falcon 180B and 180B-Chat
* Update README.md
remove Falcon 180B and 180B-Chat
* Update models.json
Add support for Starling-LM-7B-Alpha
* Update README.md
Add support for Starling-LM-7B-Alpha
* Update models.json
bugfix
2023-12-02 00:29:33 -05:00
Olivier DEBAUCHE
a4c7e8e373
Add support for TII Falcon and Meditron LLM's ( #921 )
...
* Update models.json
add Falcon 180b chat
* Update models.json
* Update models.json
* Update models.json
* Update models.json
add falcon 180b chat
* Update README.md
* Update models.json
* Update README.md
* Update models.json
* Update models.json
bugfix
* Update models.json
Add Meditron 70B
* Update README.md
Add Meditron 70B
* Update README.md
* Update models.json
bugfix
* Update models.json
Add Meditron 7B
* Update README.md
* Update models.json
* Update models.json
* Update models.json
* Update models.json
* Update models.json
* Update README.md
---------
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-12-01 07:53:05 -05:00
Juan Calderon-Perez
5c724e6f1f
Update README, remove CMAKE
2023-11-26 19:29:50 -05:00
Juan Calderon-Perez
05224d2c2c
Add support for Vicuna 7B and 13B ( #903 )
2023-11-26 15:15:52 -05:00
Juan Calderon-Perez
c7f0b487aa
Add support for GGUF models ( #866 )
2023-11-17 09:07:02 -05:00
Juan Calderon-Perez
b4190e5616
Add support for latest debian release ( #755 )
2023-09-19 22:55:19 -04:00
Juan Calderon-Perez
0500cb2266
Remove support for DragonflyDB ( #684 )
2023-09-03 23:37:23 -04:00
Juan Calderon-Perez
6c88efe5ed
Add support for WizardCoder-Python-13B-V1.0-GGML ( #681 )
2023-09-02 21:34:36 -04:00
PΔBLØ ᄃΞ
1444accc12
add: WizardCoder-Python-34B-V1.0 model ( #659 )
...
* add: WizardCoder-Python-34B-V1.0 model
* Fix json format
---------
Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-08-27 21:31:39 -04:00
Mike Zeng
6f4a396880
Adds support for LLaMA2 in the models.json ( #612 )
...
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-08-10 21:03:44 -04:00
Juan Calderon-Perez
12ec7b7f42
Support for DragonflyDB ( #598 )
2023-08-06 22:54:42 -04:00
PΔBLØ ᄃΞ
8f997f6395
Add orca and remove models don't use alpaca template ( #541 )
...
* Add orca and remove models don't use alpaca template
* Add orca and remove models don't use alpaca template
---------
Co-authored-by: pabl-o-ce <cye@poscye.com>
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-07-15 17:32:59 -04:00
Juan Calderon-Perez
da8c3e27d3
Refactor production Dockerfile, Add development Dockerfile ( #485 )
...
* Refactor Dockerfile, add Dockerfile.dev for development
* We need dev dependencies for running vite build
2023-07-01 22:47:29 -04:00
PΔBLØ ᄃΞ
c6c02271e0
Support for BigTrans, Minotaur, Robin, and Vicuna v1.3 models ( #451 )
...
* Feature: add Vicuna-v1.3-7B and Vicuna-v1.3-13B
* Feature: add BigTrans-13B
* Feature: add robin,minotour,chronos-hermes,vicuna,trans
* Feature: add robin,minotour,chronos-hermes,vicuna,trans
* Docs: update model max ram required
* Docs: update model max ram required
* Feature: add more quants q2_k,q3_K_L,q4_1,q4_K_M,q8_0 on schema.json
* Fix: missing emojis and typo vicuna models q3_K_L
* Fix: minotaur
* Fix: minotaur
* Fix: schame.json enum k-quants
* Fix: schame.json enum k-quants
---------
Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-06-19 17:16:41 -04:00
PΔBLØ ᄃΞ
6009f10fcb
Feature: Add Airoboros-1.2 models ( #435 )
...
Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-06-16 16:58:11 -04:00
PΔBLØ ᄃΞ
d1586d129a
Feature: add Chronos-Hermes-13B ( #431 )
...
Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-06-15 19:23:40 -04:00
PΔBLØ ᄃΞ
6bf84ddf8e
Add new ranked GGMLv3 models ( #417 )
...
* Feature: add some best ranked models
* Fix: models size
* Update README.md
---------
Co-authored-by: pabl-o-ce <cye@poscye.com>
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-06-12 01:31:17 -04:00
Juan Calderon-Perez
16699fac48
Update README.md
2023-06-11 16:40:33 -04:00
Juan Calderon-Perez
b1fb7009e7
Updates to README.md ( #414 )
2023-06-11 16:36:28 -04:00
Juan Calderon-Perez
dfb98c6885
Adjust headings for model names
2023-06-11 00:43:03 -04:00
Juan Calderon-Perez
70c51a457c
Structure models list in README.md ( #413 )
2023-06-11 00:40:34 -04:00
PΔBLØ ᄃΞ
634fdacc08
Feature: add new k-quants q6_K models ( #412 )
...
* Feature: add new k-quants q6_K models
* Feature: update llama-cpp-python==0.1.62
* Fix: labels and 7b not use k-quants
* Fix: labels and 7b not use k-quants
* Fix: labels and 7b old one and q6_K
* Fix: labels and 7b old sizes
* Fix: labels and 7b Koala names
---------
Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-06-10 23:28:05 -04:00
Nathan Sarrazin
0b3ad75016
it's main not latest I guess ?
2023-06-10 10:25:52 +02:00
