LocalLLaMA/typed-decisions
Viewer โข Updated โข 3.2k โข 42 โข 3
AI & ML interests
Local LLMs
Recent Activity
View all activity
codelionย
updated a
dataset about 16 hours ago
codelionย
updated a
dataset about 18 hours ago
codelionย
published 2
datasets 1 day ago
codelionย
updated a
dataset 1 day ago
codelionย
published a
Space 1 day ago
codelionย
published a
dataset 1 day ago
codelionย
updated a
Space 1 day ago
Elixpoย
submitted a
paper to Daily Papers 8 days ago
Elixpoย
authored a
paper 8 days ago
NihalGaziย
authored a
paper 9 days ago
Aurelien-Morganย
posted an update 12 days ago
Post
2419
@retrain-pipelines execution engine is in perpetual evolution, with the aim to establish itself as SOTA, and for the long run.
However, we neglect no aspect of ML-Eng centricity.
If notebooks is where you like to do dev most,
we support you there 100% too.
Build crazy combos of inline tasks, deep parallel sub-DAG branches, nested asynchronous groups...
... the DAG renderer is undergoing an incremental upgrade
until the next one.
* starring toy tasks here. No ML has been hurt in this video ๐
However, we neglect no aspect of ML-Eng centricity.
If notebooks is where you like to do dev most,
we support you there 100% too.
Build crazy combos of inline tasks, deep parallel sub-DAG branches, nested asynchronous groups...
... the DAG renderer is undergoing an incremental upgrade
until the next one.
* starring toy tasks here. No ML has been hurt in this video ๐
leonardlinย
posted an update 29 days ago
Post
185
I've trained an uploaded a proper MTP head for Ornith 1.5:
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
Post
2226
Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you 
Anthropic for supporting open source.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap โ issues and PRs welcome.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap โ issues and PRs welcome.
Post
5949
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.
CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.
See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2
Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.
See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2
Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
- 6 replies
codelionย
authored a
paper about 2 months ago
codelionย
authored 3
papers 2 months ago
pankajpandey-devย
posted an update 3 months ago
Post
4148
๐ฎ๐ณ Qwen3.5-9B Hindi Instruct โ it stops thinking in English
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
- 4 replies