Commit Graph

89 Commits

Author SHA1 Message Date
turboderp
57031e1f1b chat.py: Fix colors 2026-04-26 23:04:40 +02:00
turboderp
036cfecec7 Update branch_decode example 2026-04-25 03:17:37 +02:00
turboderp
875dbc6a9f Update generator example 2026-04-24 00:07:47 +02:00
turboderp
d602ede0eb chat.py: Optional sysprompt in chatml template 2026-04-23 19:27:25 +02:00
turboderp
f8be5ff566 Generator: Add ngram drafting 2026-04-22 13:45:07 +02:00
turboderp
2fa7593f3b model_init: Add draft model initialization 2026-04-19 19:44:34 +02:00
turboderp
0ff0e32203 Add Branch Decode demo 2026-04-13 23:40:14 +02:00
turboderp
029e50f004 chat.py: Don't list tokens with near-zero probability 2026-04-10 20:59:43 +02:00
turboderp
5a09da86c7 Update multimodal example 2026-04-08 04:01:24 +02:00
turboderp
67853a3f81 Examples: Add Gemma4 basic template 2026-04-07 22:46:12 +02:00
turboderp
0fd31f6609 chat.py: Add Gemma4 template 2026-04-05 19:44:46 +02:00
turboderp
d19844bd79 Generator: Add loop detection 2026-04-04 22:31:26 +02:00
turboderp
8a36ee8b9a chat.py: Add Qwen3.5-specific ChatML template 2026-03-21 14:16:09 +01:00
turboderp
a31d2187fc chat.py: Add probs option 2026-03-16 02:30:14 +01:00
turboderp
ebd2efb6bd chat.py: Random benchmark question feature 2026-03-13 04:31:19 +01:00
turboderp
85237d5744 chat.py: Debugging features 2026-03-07 23:29:29 +01:00
turboderp
1647c653e4 chat.py: Command help and think mode toggle 2026-03-03 23:15:07 +01:00
turboderp
a6cf34574b chat.py: Limit frequency of markdown renders 2026-03-03 22:46:32 +01:00
turboderp
021b027728 Qwen3.5: Enable MRoPE, update multimodal example 2026-03-02 05:27:33 +01:00
turboderp
c8c2e6178c chat.py: Catbench shortcut 2026-03-01 17:57:55 +01:00
turboderp
18b2a23d8a chat.py: Fix error message 2026-03-01 15:10:22 +01:00
turboderp
75ee2c78c3 Add Qwen2_5_VLForConditionalGeneration, refactor HCXVisionV2VisionModel as subclass of Qwen2_5VLVisionModel 2026-01-19 22:48:49 +01:00
turboderp
288a98f5e3 Refactor sampler args for examples 2026-01-11 12:33:27 +01:00
turboderp
a17d1a4334 Add HCXVisionV2ForCausalLM architecture 2026-01-06 16:01:54 +01:00
turboderp
6e75e7b151 chat.py: Fix for models with eos_token_id=null 2026-01-04 02:02:10 +01:00
turboderp
e8b77bba4a chat.py: Fix prompt tokens/s display 2025-12-25 23:18:50 +01:00
turboderp
80907797a5 chat.py: Add debug mode 2025-12-25 23:18:25 +01:00
turboderp
d8be5d638f chat.py: Read all stop conditions from config.json 2025-12-10 00:53:45 +01:00
turboderp
ba657d399d chat.py: Add Ministral template 2025-12-03 18:23:34 +01:00
turboderp
ef8fd43d1c Cleanup unused imports 2025-11-16 14:25:46 +01:00
turboderp
c47c17bae2 Add Glm4V-MoE architecture 2025-11-13 16:56:29 +01:00
turboderp
7c6b6c473f chat.py: Allow breaking stream with esc 2025-11-13 12:55:32 +01:00
turboderp
0bd0bfa17d chat.py: Token dump feature 2025-11-13 12:54:34 +01:00
turboderp
c3886f0841 chat.py: Don't crash on wrong stop conditions 2025-11-13 12:53:23 +01:00
turboderp
1dff8123a6 chat.py: Better SVG extract 2025-11-13 12:52:46 +01:00
turboderp
792bd9dc75 Glm4V: Update examples 2025-11-13 12:52:46 +01:00
turboderp
fcce0e6985 Fix example Mistral template 2025-11-10 01:34:26 +01:00
turboderp
8190932910 Update multimodal example 2025-11-09 13:34:11 +01:00
turboderp
20cbe13cab Update multimodal example 2025-11-09 01:42:30 +01:00
turboderp
fab5da05ce chat.py: Better SVG extraction 2025-11-02 23:54:22 +01:00
turboderp
08e88cf918 chat.py: Change default ChatML sysprompt 2025-11-01 15:59:31 +01:00
turboderp
a358e845c1 chat.py: Add (SVG) save option 2025-11-01 14:51:06 +01:00
turboderp
ef077083f9 chat.py: Fix template description 2025-11-01 14:50:51 +01:00
turboderp
8a044a4cf4 chat.py: Add MiniMax template 2025-10-31 11:18:35 +01:00
turboderp
c7f0b694b4 Update example 2025-09-19 00:48:12 +02:00
turboderp
59e3304da1 chat.py: Add Apertus template 2025-09-04 00:38:51 +02:00
turboderp
40fd9d3857 chat.py: Add Seed-OSS template 2025-08-24 21:40:26 +02:00
turboderp
d9ac8d2fd0 Fix regression #71 2025-08-16 23:39:14 +02:00
turboderp
c1b469c0ea chat.py: Add single-prompt-and-exit option 2025-08-12 18:26:16 +02:00
turboderp
921f0c4155 chat.py: Add Ctrl-C hook for cleaner multiprocess exit 2025-07-29 22:01:45 +02:00