InferenceSupport
💥
644
Discussions about the Inference Providers feature on the Hub
🔄 In a Training Loop, coming soon
Neo
textilelabs
AI & ML interests
Independent builder training small/efficient models from scratch on consumer hardware (CPU-only, no cloud). Currently exploring 1-bit/1.58-bit (BitNet-style) architectures, small language models, LoRA cartridges, and neuro-symbolic hybrids.
Recent Activity
liked a Space about 2 hours ago
huggingface/InferenceSupport new activity about 2 hours ago
huggingface/InferenceSupport:textilelabs/Loom-Spark new activity about 2 hours ago
textilelabs/Loom-Spark:🚀 Launching Loom-Spark, the first model made by textile labsOrganizations
None yet
liked a
Space about 2 hours ago
textilelabs/Loom-Spark
🔥 1
#11965 opened about 2 hours ago
by textilelabs
🚀 Launching Loom-Spark, the first model made by textile labs
#1 opened about 2 hours ago
by textilelabs
updated a
model about 3 hours ago
published a
model about 3 hours ago
reacted to CodeSoft's post with 🔥 about 22 hours ago
Post
1556
CodeSoft/sorbet-25m is out! Works out of the box with Transformers and llama.cpp
- GGUFs at CodeSoft/sorbet-25m-gguf
- Sorbet-25M-v2 (and its chat-tuned version) is in progress :)
- GGUFs at CodeSoft/sorbet-25m-gguf
- Sorbet-25M-v2 (and its chat-tuned version) is in progress :)
- 14 replies
reacted to dejanseo's post with 🔥 about 22 hours ago
Post
2930
Ox Alpha is GLM
https://dejan.ai/blog/ox-alpha/
A parameter-free k-nearest-neighbour classifier over Normalized Compression Distance (Lee et al., MobiSys ’24, Eq. 1, built on Jiang et al.'s gzip-based text classifier). NCD compares two texts by how well they compress together. C(s) is the gzip-compressed length of s. Text sharing an author's patterns compresses better together than text from a different author, so the method needs no model weights and no embeddings.
The reference corpus covers 60 prompts (essays, code, emails, dialogue, poetry) answered by five known models: GPT-5.5, Claude Opus 5, Gemini 3.7 Flash, Gemini 3.1 Pro Preview, and GLM-5.3, for 293 reference texts. ox-alpha answered the first 13 of those prompts, plus one additional novel prompt never given to the reference models beforehand, for 14 queries in total. Each query was classified against the reference corpus independently, with a k-nearest-neighbour vote (k=5):
Model ox-alpha samples matched
GLM-5.3 7 / 14
Claude Opus 5 3 / 14
Gemini 3.7 Flash 2 / 14
GPT-5.5 1 / 14
Gemini 3.1 Pro Preview 1 / 14
GLM-5.3 wins at every k tested: 7/14 at k=3, 7/14 at k=5, 6/14 at k=7, 7/14 at k=9. Claude Opus 5 is the consistent second place.
https://dejan.ai/blog/ox-alpha/
A parameter-free k-nearest-neighbour classifier over Normalized Compression Distance (Lee et al., MobiSys ’24, Eq. 1, built on Jiang et al.'s gzip-based text classifier). NCD compares two texts by how well they compress together. C(s) is the gzip-compressed length of s. Text sharing an author's patterns compresses better together than text from a different author, so the method needs no model weights and no embeddings.
The reference corpus covers 60 prompts (essays, code, emails, dialogue, poetry) answered by five known models: GPT-5.5, Claude Opus 5, Gemini 3.7 Flash, Gemini 3.1 Pro Preview, and GLM-5.3, for 293 reference texts. ox-alpha answered the first 13 of those prompts, plus one additional novel prompt never given to the reference models beforehand, for 14 queries in total. Each query was classified against the reference corpus independently, with a k-nearest-neighbour vote (k=5):
Model ox-alpha samples matched
GLM-5.3 7 / 14
Claude Opus 5 3 / 14
Gemini 3.7 Flash 2 / 14
GPT-5.5 1 / 14
Gemini 3.1 Pro Preview 1 / 14
GLM-5.3 wins at every k tested: 7/14 at k=3, 7/14 at k=5, 6/14 at k=7, 7/14 at k=9. Claude Opus 5 is the consistent second place.
- 6 replies
liked a
Space 16 days ago