GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Convergent-ch
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Convergent-ch
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Measured with greedy decoding on tasks that were never in the training data:
| Test | Result |
|---|---|
| 50 simple Python tasks of the same kind as the training data, checked by running their tests | 68 % pass |
| 20 new hand-written Python tasks with function names that never occur in the training data | 10 % pass (2 of 20) |
| 30 HTML requests: markup parses with every tag closed | 100 % |
| 30 coding requests without "codingPico": answered without a code block | 100 % |
is_prime) exists in the training data. The model mostly reproduces patterns it has seen.Use it as a toy and a demonstration of how far 7M parameters go, not as a coding assistant.
| Parameters | 6,917,376 |
| Architecture | Llama-style decoder (RMSNorm, SwiGLU, RoPE, tied embeddings) |
| Layers / hidden / MLP | 6 / 256 / 704 |
| Attention heads | 4 (head dim 64) |
| Context | 1,024 tokens |
| Vocabulary | 8,192 (byte-level BPE trained on code and chat text) |
Download pico-1.3-coding-large.gguf and Modelfile into one folder, then:
bash
ollama create pico1.3-coding-large -f Modelfileollama run pico1.3-coding-largeUse the Modelfile; without its chat template the model produces nonsense.
python
from transformers import AutoTokenizer, AutoModelForCausalLM tok = AutoTokenizer.from_pretrained("Convergent-ch/Pico-1.3-Coding-Large")model = AutoModelForCausalLM.from_pretrained("Convergent-ch/Pico-1.3-Coding-Large") ids = tok.apply_chat_template( [{"role": "user", "content": "codingPico write a function that returns the largest number in a list"}], add_generation_prompt=True, return_tensors="pt")out = model.generate(ids, max_new_tokens=150, do_sample=False)print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))Chat format: <|bos|><|user|>\n...<|end|>\n<|assistant|>\n, generation stops at <|end|>. Use temperature 0 to 0.2.
Trained from scratch in one stage on one RTX 3060 Ti with MakeAI: 3,200 steps of 32 x 1,024 tokens (about 7 passes over 14.8M tokens), AdamW, learning rate 2e-3 with cosine decay, bf16, about 12 minutes. Final validation loss 1.508 (perplexity 4.5) on held-out chats; the loss is only computed on the assistant's replies.
Training data (86,250 chats):
Apache 2.0.
ollama create pico1.3-coding-large -f Modelfileollama run pico1.3-coding-largefrom transformers import AutoTokenizer, AutoModelForCausalLM tok = AutoTokenizer.from_pretrained("Convergent-ch/Pico-1.3-Coding-Large")model = AutoModelForCausalLM.from_pretrained("Convergent-ch/Pico-1.3-Coding-Large") ids = tok.apply_chat_template( [{"role": "user", "content": "codingPico write a function that returns the largest number in a list"}], add_generation_prompt=True, return_tensors="pt")out = model.generate(ids, max_new_tokens=150, do_sample=False)print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))