WebGPU-oxcoder-9b-i1-gguf
š¤
1
Chat with an AI assistant powered by OxCoder-9B
DedeProGames PRO
DedeProGames
AI & ML interests
Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher
Recent Activity
liked a Space about 7 hours ago
localellm/WebGPU-oxcoder-9b-i1-gguf updated a dataset about 18 hours ago
DedeProGames/lm-tetris-arena-results repliedto their post 1 day ago
š Introducing Kiyo-230M-Instruct ā my compact English & Portuguese chat model!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
š§ 229.7M parameters
š English + Portuguese
š¬ Native chat template for multi-turn conversations
š 2,048-token context window
š¦ 459 MB of BF16 safetensors weights
š Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. Iām excited to share it with people exploring how much we can get from small, accessible models!
š¤ Model & full README:
https://huggingface.co/DedeProGames/Kiyo-230M-Instruct
š¬ Try the chat demo:
https://huggingface.co/spaces/DedeProGames/kiyo-230m-chat
Try it in English or Portuguese ā Iād love to see your examples, feedback, and experiments!Organizations
liked a
Space about 7 hours ago
updated a
dataset about 18 hours ago
replied to their post 1 day ago
Im from Brazil
reacted to their post with š¤Æš§ šš„ 1 day ago
Post
3,630
š Introducing Kiyo-230M-Instruct ā my compact English & Portuguese chat model!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
š§ 229.7M parameters
š English + Portuguese
š¬ Native chat template for multi-turn conversations
š 2,048-token context window
š¦ 459 MB of BF16 safetensors weights
š Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. Iām excited to share it with people exploring how much we can get from small, accessible models!
š¤ Model & full README:
DedeProGames/Kiyo-230M-Instruct
š¬ Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese ā Iād love to see your examples, feedback, and experiments!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
š§ 229.7M parameters
š English + Portuguese
š¬ Native chat template for multi-turn conversations
š 2,048-token context window
š¦ 459 MB of BF16 safetensors weights
š Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. Iām excited to share it with people exploring how much we can get from small, accessible models!
š¤ Model & full README:
DedeProGames/Kiyo-230M-Instruct
š¬ Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese ā Iād love to see your examples, feedback, and experiments!
- 3 replies
posted an update 1 day ago
Post
3,630
š Introducing Kiyo-230M-Instruct ā my compact English & Portuguese chat model!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
š§ 229.7M parameters
š English + Portuguese
š¬ Native chat template for multi-turn conversations
š 2,048-token context window
š¦ 459 MB of BF16 safetensors weights
š Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. Iām excited to share it with people exploring how much we can get from small, accessible models!
š¤ Model & full README:
DedeProGames/Kiyo-230M-Instruct
š¬ Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese ā Iād love to see your examples, feedback, and experiments!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
š§ 229.7M parameters
š English + Portuguese
š¬ Native chat template for multi-turn conversations
š 2,048-token context window
š¦ 459 MB of BF16 safetensors weights
š Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. Iām excited to share it with people exploring how much we can get from small, accessible models!
š¤ Model & full README:
DedeProGames/Kiyo-230M-Instruct
š¬ Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese ā Iād love to see your examples, feedback, and experiments!
- 3 replies
liked a
model 1 day ago
updated a
collection 1 day ago
updated a
model 1 day ago
published a
model 1 day ago
updated a
collection 1 day ago
PR
#15 opened 1 day ago
by 
DedeProGames
published a
Space 1 day ago
PR
#14 opened 1 day ago
by DedeProGames
Fix README and revert top the new fixed version
1
#13 opened 1 day ago
by DedeProGames
PLEASE LH USE THIS CARD
#12 opened 1 day ago
by DedeProGames
updated a
Space 2 days ago
Fixed "Arthurblg1802" and updated the models
4
#10 opened 2 days ago
by DedeProGames