Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-25 22:21:14 +02:00
Code Issues Packages Projects Releases Wiki Activity
9,277 Commits 3 Branches 252 Tags
8a4d31447d3759487f3cb933dddf4a4183644900
Commit Graph

51 Commits

Author SHA1 Message Date
Concedo 8a4d31447d added non thinking template for seed OSS 2025-08-23 18:19:22 +08:00
Concedo f9998b2a5d seed OSS chat templates 2025-08-23 18:01:39 +08:00
kallewoof 258f53a938 autoguess: fix Kimi search strings (#1681) 
* updated lite

* autoguess: fix Kimi search strings

* Update klite.embd

---------

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
 2025-08-11 21:55:42 +08:00
Concedo 8e6d27f629 handle if assistant_message_gen and assistant_message_gen!=assistant_message_start, replace final output tag with unspaced (gen) version if exists 2025-08-10 16:51:34 +08:00
kallewoof 204739e7f1 Adapter fixes (#1659) 
* test adapters

* add assistant_gen adapter key

* add support for chat templates stored as .jinja files

* removed mistakenly commited gated-tokenizers link

* autoguess: Harmony: add missing newline prefixes to system_end
 2025-08-10 16:19:50 +08:00
Concedo 3468c2834d fixed adv mode 2025-08-08 22:26:36 +08:00
kallewoof 866cc346ab tweak OpenAI Harmony autoguess developer prefix and assistant end token (#1673) 
* tweak OpenAI Harmony autoguess developer prefix

* use <|end|> for adapter end
 2025-08-08 21:15:11 +08:00
Concedo 338b1fe97e readjusted mistral and oai template, fixed compile issue on termux, updated lite, show generated token ids in debug mode 2025-08-07 21:14:48 +08:00
Concedo 34487d3c02 gpt oss harmony template 2025-08-06 11:39:40 +08:00
Concedo 9fbbd9e127 half measure for mistral spaced formats 2025-08-04 23:48:11 +08:00
Concedo ba626b3f4c fixes for known flaws in chat adapter. Trailing space changes in mistral not included 2025-07-27 17:00:26 +08:00
Concedo f25339c92b handle empty objects returned by tool calls, also remove misinterpretation of the tools calls instruct tag within ChatML autoguess 2025-07-25 22:22:27 +08:00
kallewoof ff8f156fa0 AutoGuess tests (#1650) 
* whitespace

* AutoGuess remove dot suffix in names

* .gitignore update

* test: added autoguess test suite

* github workflow to run autoguess test when appropriate

* git clone unavailable tokenizer configs rather than committing to repo

* fix link to included tokenizer configs

* skip storing downloaded tokenizer configs

* typo

* minor fixes

* clean-up

* limit workflow to trigger from experimental branch

---------

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
 2025-07-25 19:21:00 +08:00
Concedo e1849f9a0b updated lite (+4 squashed commit) 
Squashed commit:

[ecaa653df] updated lite

[1154c44a7] updated lite

[db2e5e43d] allow whisper interrogate mode for audio files

[490b13af8] whitespace
 2025-07-20 11:10:03 +08:00
kallewoof 226624639c AutoGuess: Move Generic cases to end of file and put Kimi with other ChatML variants (#1648) 
* AutoGuess: Move Generic cases to end of file and put Kimi with other ChatML variants

* patch Kimi ChatML template
 2025-07-18 13:24:21 +08:00
Concedo 8396add5be removed hunyuan autoguess template, fixed multi file loading up to 999 parts 2025-07-15 17:49:49 +08:00
Concedo f3f6168f85 added new autoguess templates 2025-07-15 14:51:20 +08:00
Concedo b649f69e4f gemma3n chat template 2025-06-29 15:24:55 +08:00
henk717 9c27ccde50 RWKV World chat adapters (#1612) 2025-06-20 21:39:59 +08:00
Concedo 1cf7648305 fixed adapter 2025-06-08 23:24:11 +08:00
Concedo ae8f01c2d4 no need for chat start for now 2025-05-22 23:19:29 +08:00
Concedo 8b6dfbd1be disabling the gMask prefix for glm-4 completions 2025-05-21 17:29:24 +08:00
Concedo d4316aa4ed fixed bad template 2025-05-15 00:44:48 +08:00
Concedo 11984f1040 fixed autoguess adapters, fixed tool builds 2025-05-13 19:38:56 +08:00
Concedo fda682fa12 updated lite 2025-04-30 19:49:54 +08:00
Concedo e561eeb5e5 qwen3 no think template fix 2025-04-29 21:06:27 +08:00
Concedo c2802af9e8 fix qwen3, fixed sd, fixed glm4 2025-04-29 20:50:46 +08:00
Concedo 4d8a7a6594 fix occasional clip segfault, fix glm4 (+1 squashed commits) 
Squashed commits:

[bd71cd688] GLM4 fix wip
 2025-04-29 01:42:50 +08:00
kallewoof 7cb815b727 AutoGuess: GLM-4 (#1502) 
* AutoGuess: GLM-4

* add 'chat_start' field to adapters

* GLM-4 fix
 2025-04-26 08:47:42 +08:00
Concedo d32d0b382a glm4 template 2025-04-25 00:41:15 +08:00
Concedo a6149ad0fc fixed g3 adapter back 2025-04-12 23:17:54 +08:00
Concedo c94aec1930 update workflows, update gemma default adapter sysprompt 2025-04-12 18:38:23 +08:00
Concedo efef14bb82 added llama4 tags 2025-04-12 08:58:04 +08:00
Concedo 93a226d9e4 added prefix for llava, reverted system role in template as it degreaded gemma3. truncated debug logs 2025-04-05 18:06:41 +08:00
Concedo 669311365c fixed gemma system prompt 2025-04-02 13:58:51 +08:00
Concedo 0ed95fcccc fixed l3 template, add index 2025-03-31 23:59:06 +08:00
Concedo 6a1dd57435 gemma3 template, updated lite, fixed tool calling, reenable ctx shift for gemma3 2025-03-14 17:47:01 +08:00
Concedo 6b7d2349a7 Rewrite history to fix bad vulkan shader commits without increasing repo size 
added dpe colab (+8 squashed commit)

Squashed commit:

[b8362da4] updated lite

[ed6c037d] move nsigma into the regular sampler stack

[ac5f61c6] relative filepath fixed

[05fe96ab] export template

[ed0a5a3e] nix_example.md: refactor (#1401)

* nix_example.md: add override example

* nix_example.md: drop graphics example, already basic nixos knowledge

* nix_example.md: format

* nix_example.md: Vulkan is disabled on macOS

Disabled in: https://github.com/NixOS/nixpkgs/commit/1ccd253accfb140acbf9da9f56d9dc6d3aece088

* nix_examples.md: nixpkgs.config.cuda{Arches -> Capabilities}

Fixes: https://github.com/LostRuins/koboldcpp/issues/1367

[675c62f7] AutoGuess: Phi 4 (mini) (#1402)

[4bf56982] phrasing

[b8c0df04] Add Rep Pen to Top N Sigma sampler chain (#1397)

- place after nsigma and before xtc (+3 squashed commit)

Squashed commit:

[87c52b97] disable VMM from HIP

[ee8906f3] edit description

[e85c0e69] Remove Unnecessary Rep Counting (#1394)

* stop counting reps

* fix range-based initializer

* strike that - reverse it
 2025-03-05 00:02:20 +08:00
Concedo cca4a934dd fix for chat templates and drafting 2025-01-23 11:49:40 +08:00
kallewoof 1cb9805024 add autoguess adapter for DeepSeek V2.5/R1 (#1329) 2025-01-22 20:39:04 +08:00
kallewoof 23ec550835 PoC: add chat template heuristics (#1283) 
* PoC: add chat template heuristics

The fallback chat template adapter of Vicuna is not ideal in some cases (e.g. a test against a sub-portion of the BBC news classification task on Kaggle gave an 82% accuracy with Vicuna and 88% with the official ChatML format for a q4_k_m Qwen 2.5 3B-Instruct gguf).

This PR adds a proof of concept simple heuristic which looks at the chat template and upgrades the adapter when it is able to.

* gemma 2 heuristic

* Phi 4, Llama 3.x heuristics

* better qwen vs generic heuristic

* cleanup

* mistral (generic) heuristic

* fix sys msg for mistral

* phi 3.5

* mistral v3

* cohere (aya expanse 32b based)

* only derive from chat template if AutoGuess

* add notes about alpaca fallbacks

* added AutoGuess.json dummy

* add mistral v7

* switch to using a json list with search strings
 2024-12-28 12:15:23 +08:00
Concedo a577015425 consolidate mistral templates (too many) 2024-12-15 00:03:34 +08:00
pandora a548108dd2 Create Mistral-V7.json (#1224) 2024-11-19 10:45:50 +08:00
Concedo c38d1ecc8d update templates, fix rwkv 2024-09-22 01:32:12 +08:00
pandora d4d19f6dbe Fixing Mistral Templates (#1131) 
* Update and rename Mistral.json to Mistral V1.json

* Create Mistral V2 & V3

* Rename Mistral V2 & V3 to Mistral V2 & V3.json

* Create Mistral V3-Tekken.json
 2024-09-22 01:30:17 +08:00
xzuyn add0a88111 Update kcpp_adapters (#985) 
* Update kcpp_adapters

* Update kcpp_adapters
 2024-07-13 19:06:15 +08:00
Nexesenex c9c098dab2 Add mistral chat adapter (#983) 2024-07-09 19:38:35 +08:00
Concedo 5e458f42da update gemma format 2024-07-06 18:54:20 +08:00
Concedo 82202aebda updated lite, add gemma 2 template 2024-07-02 21:02:52 +08:00
henk717 8421243c6d Chat Adapters (#956) 
* Give the CI builds a recognizable AVX1 name

* Chat Adapters
 2024-06-30 10:28:43 +08:00