GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
textilelabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
textilelabs
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Every prior full-size Loom release (v1, 1.5, 1.8) only learned <|endoftext|> at the
very end of a whole training document — mid-conversation, nothing told the model a turn
had ended, so on a runtime without exactly the right stop-token setup it would keep
generating and invent your next message itself. This happened to the founder testing
Loom Spark 1.8 in Ollama the day it shipped.
This model's curriculum was rebuilt so <|endoftext|> follows every single reply,
not just document end. Verified: 442,333 / 442,333 model turns in the training corpus
end in EOS. Tested with zero configuration — Ollama's stock chat template, no
Modelfile, no stop tokens set by hand: 0 self-dialogue turns, both through the
default chat endpoint and through the real agent harness with live web search. It stops
because it learned to.
Both were trained on the identical 70MB curriculum and tokenizer. The only difference is capacity (128d×4L×4H vs 192d×4L×4H) and training budget, matched by step count (2,625 vs 2,666 steps) rather than wall-clock minutes — an earlier version of this model was trained for equal minutes instead of equal steps, which under-trained it relative to 1.5 Flash despite being bigger. That run was discarded; these are the numbers from the properly step-matched retrain.
| 1.5 Flash | 1.8 Flash | |
|---|---|---|
| Params | 1.35M | 2.62M |
| Val loss | 0.3544 | 0.3332 |
| Identity probes leaking | 0/12 | 0/12 |
| Offline fact leak (raw model) | 18/30 | 15/30 |
| Clean online lookups | 5/10 | 6/10 |
| Self-terminates, zero config | ✅ | ✅ |
Still a very small model. Expect wrong or garbled answers to most factual questions — there's more room here than 1.5 Flash for identity and structure to hold up, but a real fact-core still doesn't fit. What holds up well: identity, restraint, and emotional register — 0/12 identity probes leaked, matching the best of the full-size models.
markdown
<tools:off><tools:off><user> who are you<loom>
No trailing space after <loom>. With tools on, a reply may end in
<lookup>query</lookup><|endoftext|>; your harness splices in <result>…</result>
before continuing.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("textilelabs/Loom-Spark-1.8-Flash")model = AutoModelForCausalLM.from_pretrained("textilelabs/Loom-Spark-1.8-Flash")prompt = "<tools:off>\n<tools:off><user> who are you\n<loom>"ids = tok(prompt, return_tensors="pt", add_special_tokens=False).input_idsout = model.generate(ids, max_new_tokens=100, do_sample=True,temperature=0.8, top_k=50, pad_token_id=tok.eos_token_id)print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False))
bash
ollama create loom-spark-1.8-flash -f ollama/Modelfileollama run loom-spark-1.8-flash
Safe to run with no Modelfile at all — ollama run hf.co/textilelabs/Loom-Spark-1.8-Flash
will not talk to itself, though output quality is better with the correct template.
bash
pip install ./harnessloom-chat --model textilelabs/Loom-Spark-1.8-Flash
Harness v0.2.2+ required — auto-detects this model's format via an explicit flag in
config.json rather than guessing from parameter count.
markdown
config.json / model.safetensors transformers weightstokenizer.json / tokenizer_config.json 4096-token custom BPE (Flash-specific)loom-spark-1.8-flash-f32.gguf GGUF for llama.cpp / Ollamaollama/Modelfile correct template + stop tokensharness/ agent harness v0.2.2 with web searchevaluation/ acceptance logs, comparison vs 1.5 Flash
MIT. See LICENSE.