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 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 any runtime without the exact right stop-token configuration, it would keep going
and invent your next message itself. This happened to the founder testing 1.8 in
Ollama the day it shipped.
Loom Spark 1.5 Flash's curriculum was rebuilt so <|endoftext|> follows every single
reply, not just the end of a document. 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 — across chat and raw completion
endpoints: 0 self-dialogue turns. It stops because it learned to, not because a
runtime told it to.
At 1.35M parameters there is essentially no room left for facts once identity and conversational structure are learned. Expect:
<lookup> leakage on raw-model factual questions (18/30 measured,
in line with the rest of the Loom line — see evaluation/RESULTS.md).markdown
<tools:off><tools:off><user> who are you<loom>
No trailing space after <loom> — see the mainline card for why that matters.
With tools on, a reply may end in <lookup>query</lookup><|endoftext|>; your harness
splices in <result>…</result> before continuing. Because of the EOS-every-turn fix,
the model reliably stops even without a harness — the harness's <result> injection is
still required for it to actually know anything found online, but nothing forces you to
run one just to get a well-formed single reply.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("textilelabs/Loom-Spark-1.5-Flash")model = AutoModelForCausalLM.from_pretrained("textilelabs/Loom-Spark-1.5-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-1.5-flash -f ollama/Modelfileollama run loom-spark-1.5-flash
Unusually for a base-style Loom model, this one is also safe to run with no
Modelfile at all — ollama run hf.co/textilelabs/Loom-Spark-1.5-Flash will not
talk to itself, though output quality is better with the correct template and stop
tokens, which the Modelfile provides.
bash
pip install ./harnessloom-chat --model textilelabs/Loom-Spark-1.5-Flash
Harness v0.2.2+ required — it auto-detects this model's per-turn marker format via an
explicit flag in config.json rather than guessing from model size, since this model
is far smaller than earlier heuristics assumed any Loom model would be.
markdown
config.json / model.safetensors transformers weightstokenizer.json / tokenizer_config.json 4096-token custom BPE (Flash-specific)loom-spark-1.5-flash-f32.gguf GGUF for llama.cpp / Ollamaollama/Modelfile correct template + stop tokensharness/ agent harness v0.2.2 with web searchevaluation/ acceptance logs, self-termination proof
MIT. See LICENSE.