unsloth/GLM-5.2-GGUF
Text Generation • 754B • Updated • 22.6k • 202
Jeremy Haschal
JermemyHaschal
AI & ML interests
None yet
Recent Activity
liked a model 4 days ago
unsloth/GLM-5.2-GGUF new activity 9 days ago
TheDrummer/Rocinante-XL-16B-v1-GGUF:Query new activity 2 months ago
cstr/parakeet-tdt-0.6b-v3-GGUF:CrispASR repo is gone - What to do?Organizations
None yet
liked a
model 4 days ago
CrispASR repo is gone - What to do?
2
#1 opened 2 months ago
by JermemyHaschal
FP8 version
#1 opened 2 months ago
by JermemyHaschal
reacted to albertvillanova's post with 🤗 4 months ago
Post
2948
🚀 TRL v0.29.0 introduces trl-training: an agent-native training skill.
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
reacted to OzTianlu's post with 🤗 4 months ago
Post
3465
O(1) inference is the foundational design of Spartacus-1B-Instruct 🛡️ !
NoesisLab/Spartacus-1B-Instruct
We have successfully replaced the KV-cache bottleneck inherent in Softmax Attention with Causal Monoid State Compression. By defining the causal history as a monoid recurrence, , the entire prefix is lossily compressed into a fixed-size state matrix per head.
The technical core of this architecture relies on the associativity of the monoid operator:
Training: parallel prefix scan using Triton-accelerated JIT kernels to compute all prefix states simultaneously.
Inference: True sequential updates. Memory and time complexity per token are decoupled from sequence length.
Explicit Causality: We discard RoPE and attention masks. Causality is a first-class citizen, explicitly modeled through learned, content-dependent decay gates.
Current zero-shot benchmarks demonstrate that Spartacus-1B-Instruct (1.3B) is already outperforming established sub-quadratic models like Mamba-1.4B and RWKV-6-1.6B on ARC-Challenge (0.3063). Recent integration of structured Chain-of-Thought (CoT) data has further pushed reasoning accuracy to 75%.
The "Spartacus" era is about scaling intelligence, not the memory wall ♾️.
NoesisLab/Spartacus-1B-Instruct
We have successfully replaced the KV-cache bottleneck inherent in Softmax Attention with Causal Monoid State Compression. By defining the causal history as a monoid recurrence, , the entire prefix is lossily compressed into a fixed-size state matrix per head.
The technical core of this architecture relies on the associativity of the monoid operator:
Training: parallel prefix scan using Triton-accelerated JIT kernels to compute all prefix states simultaneously.
Inference: True sequential updates. Memory and time complexity per token are decoupled from sequence length.
Explicit Causality: We discard RoPE and attention masks. Causality is a first-class citizen, explicitly modeled through learned, content-dependent decay gates.
Current zero-shot benchmarks demonstrate that Spartacus-1B-Instruct (1.3B) is already outperforming established sub-quadratic models like Mamba-1.4B and RWKV-6-1.6B on ARC-Challenge (0.3063). Recent integration of structured Chain-of-Thought (CoT) data has further pushed reasoning accuracy to 75%.
The "Spartacus" era is about scaling intelligence, not the memory wall ♾️.
Comparison with Rivermind-Lux-12B-v1b?
4
#1 opened 4 months ago
by JermemyHaschal
reacted to Reubencf's post with 🔥 5 months ago
Post
2224
📢 New release! World_events Dataset now available featuring global events spanning 2023 through 2025
🌍 https://huggingface.co/collections/Reubencf/world-events
🚀 2026 dataset dropping soon
🌍 https://huggingface.co/collections/Reubencf/world-events
🚀 2026 dataset dropping soon
- 1 reply
Joytag no longer works
4
#14 opened 8 months ago
by 
bro123123
ERROR: Could not detect model type of: D:\...\Chroma1-Radiance-v0.1.safetensors
7
#2 opened 9 months ago
by 
Viennar
updated a
model 10 months ago
published a
model 10 months ago
HF Space?
10
#4 opened 11 months ago
by JermemyHaschal
liked a
model 11 months ago
Using tags?
3
#5 opened 11 months ago
by JermemyHaschal
Please use `--jinja` or else gibberish!
❤️🚀 2
1
#2 opened 12 months ago
by 
danielhanchen
Use with other model?
2
#3 opened 12 months ago
by JermemyHaschal
Difference between normal and 'detail-calibrated'?
👍 3
3
#13 opened 12 months ago
by JermemyHaschal
Mistral-Nemo-Instruct-2407 compatibility?
3
#1 opened about 1 year ago
by JermemyHaschal
Request?
1
#1 opened over 1 year ago
by 
BlueNipples