Quantized
Collection
Quantized models by me • 14 items • Updated
🔄 In a Training Loop
Nikita Davidchuk
Ar4ikov
AI & ML interests
nlp, web, opensource, transformers, asr, ser, tts, cv
Recent Activity
updated a collection 15 days ago
Quantized liked a dataset 21 days ago
nvidia/simready-assets updated a model 26 days ago
Ar4ikov/decider-4b-AWQ-ASYM-W4A16Organizations
updated a
collection 15 days ago
liked a
dataset 21 days ago
updated a
model 26 days ago
published a
model 26 days ago
reacted to Banaxi-Tech's post with 🔥 27 days ago
Post
3,820
KV1 updates:
We at
klein-ml have finished stage 1 of KV1 1.2B, we don't think we will need additional stages.
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at klein-ml are working on Klein 24B A2B which will be our first model featuring ternary weight quantization.
We at
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at
- 4 replies
liked a
model 29 days ago
upvoted a collection 29 days ago
liked a
model about 1 month ago
liked 3
Spaces about 1 month ago
liked a
model about 1 month ago
reacted to pollix's post with 🚀 about 1 month ago
Post
6,457
stuntd 0.1.2 is out 🎉
stuntd sits in front of your LLM, learns its typed decisions and answers the confident ones locally with a small head on the Laya encoder by @convaiinnovations . About 20ms on GPU and 60ms on CPU, and anything it isn't sure about still goes to the big model.
New in 0.1.2:
- decisions with several fields, like category + urgency + needs_human in one call, answered locally only when every field is sure
- the Anthropic Messages API learns too, not only OpenAI
- auto_retrain: the daemon retrains a site in the background once enough new traffic comes in, so collect, train, shadow and live run on their own
- serve --lazy loads the checkpoint on the first request
Try it in the browser: pollix/stuntd
Code: https://github.com/bladedevoff/stuntd
stuntd sits in front of your LLM, learns its typed decisions and answers the confident ones locally with a small head on the Laya encoder by @convaiinnovations . About 20ms on GPU and 60ms on CPU, and anything it isn't sure about still goes to the big model.
New in 0.1.2:
- decisions with several fields, like category + urgency + needs_human in one call, answered locally only when every field is sure
- the Anthropic Messages API learns too, not only OpenAI
- auto_retrain: the daemon retrains a site in the background once enough new traffic comes in, so collect, train, shadow and live run on their own
- serve --lazy loads the checkpoint on the first request
Try it in the browser: pollix/stuntd
Code: https://github.com/bladedevoff/stuntd
pip install -U stuntd
- 1 reply
updated 4
models about 2 months ago
Ar4ikov/VibeVoice-ASR-DFlash2
Automatic Speech Recognition • 9B • Updated • 36
Ar4ikov/VibeVoice-ASR-AWQ-W4A16-ASYM-DFlash2
Automatic Speech Recognition • 8B • Updated • 37
Ar4ikov/VibeVoice-ASR-DFlash2-Drafter-AWQ-W4A16-ASYM
Automatic Speech Recognition • 0.8B • Updated • 46
Ar4ikov/VibeVoice-ASR-DFlash2-Drafter
Automatic Speech Recognition • 0.8B • Updated • 46
updated a
collection about 2 months ago
published a
model about 2 months ago
updated a
collection about 2 months ago