GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CastIronMind
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CastIronMind
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The smallest My Little Pony language model we could find: 32 million parameters and 64 MB of weights. This is the supervised checkpoint, tuned for character-driven conversation.
<system> / <user> / <assistant> layout described in section 6.| field | value |
|---|---|
| Type | Causal Language Model |
| Training stage | Pretraining from scratch, then supervised fine-tuning |
| Architecture | Llama |
| Parameters | 31,990,272 (32M) |
| Layers | 8 |
| Hidden size | 512 |
| Attention heads | 16 (2 key/value heads) |
| Head dimension | 32 |
| Intermediate size | 1,536 |
| Context length | 1,024 tokens |
| Vocabulary | 16,384 (byte-level BPE) |
| Tied embeddings | yes |
| Precision | bfloat16 |
| License | Apache 2.0 |
| model | parameters | weights | best for |
|---|---|---|---|
| LissaNano-Base | 32M | 64 MB | continued pretraining, research |
| LissaNano-Instruct | 32M | 64 MB | phones, single-board computers, embedded use |
| LissaBrat-Base | 103M | 206 MB | continued pretraining, research |
| LissaBrat-Instruct | 103M | 206 MB | laptops, longer and more coherent text |
| Lissa 1.5B Instruct | 1.45B | 2.9 GB | a full roleplay partner |
| Lissa 1.5B Base | 1.45B | 2.9 GB | pretraining, research |
GGUF quantizations: LissaNano-Instruct-GGUF — 15 files from Q8_0 down to IQ2, each with measured perplexity against this bf16 checkpoint.
Demo: Lissa Playground — compare quantizations side by side in the browser, no server.
text
pip install torch transformersNo custom kernels and no exotic dependencies: this is a plain Llama checkpoint and loads with any recent transformers.
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "CastIronMind/LissaNano-Instruct"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16)model.eval() SYS, USR, AST, EOS = 2, 3, 4, 1 system = "You are Twilight Sparkle, a studious purple unicorn who loves books."user = "Twilight, I found a strange book in the library." ids = [SYS] + tok.encode(system, add_special_tokens=False) \ + [USR] + tok.encode(user, add_special_tokens=False) + [AST]x = torch.tensor([ids], dtype=torch.long) out = model.generate(x, max_new_tokens=120, do_sample=True, temperature=0.8, top_p=0.9, repetition_penalty=1.1, pad_token_id=0, eos_token_id=EOS)print(tok.decode(out[0][len(ids):], skip_special_tokens=True))The model was supervised on exactly this layout:
text
<system>{persona}<user>{message}<assistant>{reply}<eos>Tags are concatenated without spaces. A non-empty system message is required: every supervised example carried one.
Special tokens. 0 <pad>, 1 <eos>, 2 <system>, 3 <user>, 4 <assistant>.
Sampling. Temperature 0.8, top_p 0.9, repetition penalty 1.1.
Pretraining. Fandom prose and forums from the My Little Pony community, about 1 billion unique tokens, two epochs.
Supervised fine-tuning. Roleplay and persona dialogues with the <system> / <user> / <assistant> layout, two epochs.
This checkpoint is tuned for dialogue, so held-out perplexity is reported on the base model card, where it is measured on the same frozen set for every model in the family: see LissaNano-Base.
What the supervised stage targets: character voice, in-persona dialogue, and stable formatting across turns.
| item | value |
|---|---|
| Training hardware | one consumer GPU |
| Authors | one person |
| Weights on disk | 64 MB (bfloat16) |
| License | Apache 2.0 |
Apache License 2.0. Use it, fine-tune it, quantize it, embed it, and publish your own versions.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "CastIronMind/LissaNano-Instruct"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16)model.eval() SYS, USR, AST, EOS = 2, 3, 4, 1 system = "You are Twilight Sparkle, a studious purple unicorn who loves books."user = "Twilight, I found a strange book in the library." ids = [SYS] + tok.encode(system, add_special_tokens=False) \ + [USR] + tok.encode(user, add_special_tokens=False) + [AST]x = torch.tensor([ids], dtype=torch.long) out = model.generate(x, max_new_tokens=120, do_sample=True, temperature=0.8, top_p=0.9, repetition_penalty=1.1, pad_token_id=0, eos_token_id=EOS)print(tok.decode(out[0][len(ids):], skip_special_tokens=True))