GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aungkomyint
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
aungkomyint
Model Tree
aungkomyint/tara1.1
Input Modalities
Output Modalities
Supported Functionality
tara1.3tara-1.3-ai-engineer-toolcall-sft-v4-plaintok-from300/checkpoint-100LlamaForCausalLMsafetensorsTara 1.3 is designed to produce JSON-style tool calls for a small AI-engineering tool set.
Supported tool names:
weathersearchsegmentevaluate_modeltrain_sftinspect_fileextract_jsonnoneExample target shapes:
json
{"tool":"weather","location":"Bangkok tomorrow"}json
{"tool":"search","query":"Python list comprehension examples"}json
{"tool":"train_sft","base_model":"models/base","dataset":"data/train.txt","output_dir":"outputs/run"}json
{"tool":"none","response":"Tokenizer validation passed. Next, run a small generation smoke test."}python
import jsonimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "aungkomyint/tara1.3" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id)model.eval() def generate_tool_call(user_text): prompt = f"User: {user_text.strip()}\nAssistant:\n" inputs = tokenizer(prompt, return_tensors="pt") inputs.pop("token_type_ids", None) with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=120, do_sample=False, repetition_penalty=1.08, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) text = tokenizer.decode(output[0], skip_special_tokens=False) reply = text[len(prompt):] if text.startswith(prompt) else text.split("Assistant:", 1)[-1] reply = reply.split("<|endoftext|>", 1)[0].split("<|pad|>", 1)[0].strip() return reply reply = generate_tool_call("Search the web for Python list comprehension examples.")print(reply) try: parsed = json.loads(reply) print("tool:", parsed.get("tool"))except json.JSONDecodeError: print("Model did not return valid JSON for this sample.")Use a simple instruction format:
text
User: <request>Assistant:Greedy decoding is recommended for tool-call tests:
text
do_sample=Falsemax_new_tokens=120repetition_penalty=1.08Tara 1.3 was trained as a supervised fine-tuning continuation for AI-engineering tool calls.
Training configuration:
Dataset:
The released checkpoint was selected from a small local comparison on 2026-06-24.
The 10-prompt eval covered weather, search, segmentation, model evaluation, SFT training, file inspection, JSON extraction, and no-tool/general responses.
| Checkpoint | Valid JSON | Schema OK | Expected Tool Match |
|---|---|---|---|
checkpoint-100 | 6/10 | 5/10 | 5/10 |
checkpoint-200 | 5/10 | 5/10 | 5/10 |
checkpoint-300 | 5/10 | 5/10 | 5/10 |
checkpoint-100 was selected because it tied the other continued checkpoints on schema correctness and tool selection while producing one more valid JSON output.
Tokenizer validation passed: tool-call JSON tokenizes through the plain BPE vocabulary without old chat/tool special tokens.
tool: "none" responses are unstable.Applications should:
tool name against an allowlist.If you use this model, cite it as:
text
Aung Ko Myint. Tara 1.3. 2026. Hugging Face model checkpoint.import jsonimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "aungkomyint/tara1.3" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id)model.eval() def generate_tool_call(user_text): prompt = f"User: {user_text.strip()}\nAssistant:\n" inputs = tokenizer(prompt, return_tensors="pt") inputs.pop("token_type_ids", None) with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=120, do_sample=False, repetition_penalty=1.08, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) text = tokenizer.decode(output[0], skip_special_tokens=False) reply = text[len(prompt):] if text.startswith(prompt) else text.split("Assistant:", 1)[-1] reply = reply.split("<|endoftext|>", 1)[0].split("<|pad|>", 1)[0].strip() return reply reply = generate_tool_call("Search the web for Python list comprehension examples.")print(reply) try: parsed = json.loads(reply) print("tool:", parsed.get("tool"))except json.JSONDecodeError: print("Model did not return valid JSON for this sample.")User: <request>Assistant:do_sample=Falsemax_new_tokens=120repetition_penalty=1.08Aung Ko Myint. Tara 1.3. 2026. Hugging Face model checkpoint.{"tool":"weather","location":"Bangkok tomorrow"}{"tool":"search","query":"Python list comprehension examples"}{"tool":"train_sft","base_model":"models/base","dataset":"data/train.txt","output_dir":"outputs/run"}{"tool":"none","response":"Tokenizer validation passed. Next, run a small generation smoke test."}