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
Prefix your prompt with a mode header:
markdown
<tools:off><user> what year did the Titanic sink?<loom> That's outside my little head...
markdown
<tools:on><user> what year did the titanic sink?<loom> Not stored in here, thankfully. Searching: <lookup>titanic sinking date</lookup><|endoftext|><result>The Titanic sank on 15 April 1912.</result><loom> April 1912 ...
The <result> block is injected by YOUR harness after executing the search.
Stop generation at <|endoftext|> or <user>.
python
from transformers import GPT2LMHeadModel, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("TextileLabs/loom-spark")model = GPT2LMHeadModel.from_pretrained("TextileLabs/loom-spark")prompt = "<tools:off>\n<user> who are you?\n<loom>"ids = tok(prompt, return_tensors="pt").input_idsout = model.generate(ids, max_new_tokens=90, do_sample=True, temperature=0.85,top_k=50, pad_token_id=tok.eos_token_id)print(tok.decode(out[0][ids.shape[1]:]))
In offline mode the harness-style markup never appears — lookup tokens are
trained/banned out of distribution under <tools:off>.
Tested on transformers ≥ 4.40 (both 4.x and 5.x) and Python 3.9–3.13. The playground widget above prefills the correct prompt format — keep the
<tools:…>header and trailing<loom>or output quality drops sharply.
loom-spark-f32.gguf (in this repo) carries the same weights plus the custom
BPE tokenizer with all nine special tokens embedded. Feed it the mode-header
prompt format shown above and stop at <|endoftext|> or <user>:
bash
llama-cli -m loom-spark-f32.gguf \-p "<tools:off>\n<user> who are you?\n<loom>" -n 128 --temp 0.85 --top-k 50
The default Ollama template does NOT fit this model (it will ramble). Use the
Modelfile shipped in ollama/:
bash
ollama pull hf.co/textilelabs/Loom-Sparkcurl -L -O https://huggingface.co/textilelabs/Loom-Spark/resolve/main/ollama/Modelfileollama create loom-spark -f Modelfileollama run loom-spark "hi"
The Modelfile keeps multi-turn history in the trained format (each past turn is
re-wrapped in <user>/<loom> markers) and stops generation cleanly. That
gives the offline persona: greetings, identity, honest deferrals, made-up words.
Two honest caveats: if a reply ends in a <lookup>…</lookup> line, that's the
model saying "I'd search for this" — raw runners can't execute searches, so
for real internet answers use the harness (Option C). And at temperature 0.85 a
7M model occasionally misreads intent ("whats your name?" sometimes gets a
philosophy answer; ask again or drop --temperature 0.7). Both quirks shrink
in Loom Spark v2's curriculum.
Note: without a wrapper that executes <lookup> calls and splices <result>
blocks back in, GGUF/Ollama runners get the model's honest "I don't know, but
here's what I'd look up" side. That is by design.
This repo ships harness/, a small pip package that gives Loom Spark real,
keyless web search (DuckDuckGo) through a terminal chat (loom-chat) and a
local web GUI (loom-web). It intercepts the model's <lookup> calls, runs
the search, injects <result>, and lets the model summarize — exactly the
loop it was trained for.
bash
# download this repo, then:pip install ./harnessloom-chat # terminal, internet onloom-web --port 7860 # local chat GUI with a tools on/off switch
Or drive it from Python:
python
from loomspark_harness.loader import load_model_and_tokenizerfrom loomspark_harness.agent import LoomAgentfrom loomspark_harness.search import get_backendmodel, tok, block = load_model_and_tokenizer("TextileLabs/loom-spark")agent = LoomAgent(model, tok, backend=get_backend("duckduckgo"), block_size=block)print(agent.reply("what's the tallest mountain?")["text"])
Decoder-only transformer, pre-LN GELU blocks, tied embeddings, learned positions.
| layers | 5 |
| heads | 5 (head_dim 64) |
| d_model | 320 |
| context | 256 tokens |
| vocab | 4096 (custom BPE trained only on our generated corpus) |
| params | ≈ 7.6M (7,558,080) |
Trained entirely on a procedurally generated, fully owned curriculum (dialogue + simple prose; zero external datasets), CPU-only fp32 AdamW, 3,337 steps, final validation loss 0.3372.
Loom Spark knows almost nothing. That is the point. Do not use it for facts, medicine, law, finance, or anything where being wrong costs more than company.