GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
oddadmix
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
oddadmix
Model Tree
oddadmix/50M-2048-Emhotob
Input Modalities
Output Modalities
Supported Functionality
| Parameters | ~51.8M |
| Architecture | Llama (LlamaForCausalLM) |
| Hidden size | 512 · Layers 12 · Heads 8 (GQA, 4 KV) · head_dim 64 |
| Vocab size | 32002 (32000 base + 2 ChatML control tokens) |
| Context length | 2048 |
| Chat format | ChatML (`< |
| Precision | bfloat16 |
| License | Apache-2.0 (matches the base architecture) |
The model is the end of a base → SFT → distillation → RL pipeline, all in pure 🤗 Transformers (no TRL — the GRPO loop is from scratch):
oddadmix/50M-2048-Emhotob,
pre-trained from scratch on ~20B Arabic tokens (2048 ctx), architecture and training
scripts derived from SupraLabs/Supra-50M-Base.<tool_call> format).LiquidAI/LFM2-1.2B-Tool)
generated targets — including fluent Arabic abstentions and hard-negative
(no-matching-tool) examples — that the student learned to imitate. This is the
variant that reliably declines out-of-scope requests.What the experiment found (the POC result): at 50M parameters there is a genuine precision ↔ recall frontier on the call decision — you can maximize valid calls or maximize correct refusals, but not both. GRPO with a perfect verifiable reward moves along this frontier rather than beyond it; this checkpoint deliberately sits at the robust-abstention corner. (A separately-tested 2.5× larger student tied these metrics, corroborating that the ceiling is capacity, not the training signal.)
Numbers are reported honestly for this exact checkpoint against the sibling SFT/RL checkpoints (see the training repo for the full trial log).
Dialect eval (18 items, Egyptian-dialect prompts):
| metric | this model | note |
|---|---|---|
| strict success | 12/18 | headline |
| decision (call/answer correct) | 16/18 | |
| abstention | 4/4 ✅ | robustly declines out-of-scope requests |
MSA eval v2 (126 items, higher-resolution): strict 11/68, decision 49/68, abstain 27/46 — the high-abstention end of the decision↔abstain frontier. Tool-selection (~33%) and argument-exactness (~18%) are the capacity-bound bottlenecks shared across all checkpoints at this scale.
The tokenizer uses the TokenizersBackend class, which requires transformers>=5.12.
Build the ChatML prompt manually and pass the tool schema in the system message:
python
import json, torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "oddadmix/Emhotob-50M-GPRO-Arabic-Final"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16) tools = [{ "name": "get_weather", "description": "Get the current weather for a city", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]},}] system = ( "أنت مساعد يستطيع استدعاء الأدوات. الأدوات المتاحة:\n" + json.dumps(tools, ensure_ascii=False) + "\nإذا لم تكن هناك أداة مناسبة، اعتذر ولا تختلق استدعاءً.")user = "ما حالة الطقس في القاهرة؟" prompt = ( f"<|im_start|>system\n{system}<|im_end|>\n" f"<|im_start|>user\n{user}<|im_end|>\n" f"<|im_start|>assistant\n")ids = tok(prompt, return_tensors="pt").to(model.device)out = model.generate( **ids, max_new_tokens=256, do_sample=False, repetition_penalty=1.2, eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"),)print(tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True))# Expected: <tool_call>{"name": "get_weather", "arguments": {"location": "القاهرة"}}</tool_call>For an out-of-scope request with no matching tool, the model is tuned to refuse in Arabic rather than hallucinate a call.
Intended use. Research and demonstration of Arabic tool-calling / agentic behavior at tiny scale; a CPU-friendly baseline for from-scratch Arabic SLM experiments.
Limitations. At ~50M parameters this is a proof of concept. Tool-selection with several confusable tools (~33% correct) and exact argument extraction (~18%) are the capacity-bound weak spots — validate any tool call before executing it. Training was predominantly Modern Standard Arabic; dialect prompts are harder. Not for production agents without a validation/guardrail layer.
LiquidAI/LFM2-1.2B-Tool.SupraLabs/Supra-50M-Base (Apache-2.0).oddadmix/50M-2048-Emhotob — from-scratch, ~20B Arabic tokens, 2048 ctx.import json, torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "oddadmix/Emhotob-50M-GPRO-Arabic-Final"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16) tools = [{ "name": "get_weather", "description": "Get the current weather for a city", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]},}] system = ( "أنت مساعد يستطيع استدعاء الأدوات. الأدوات المتاحة:\n" + json.dumps(tools, ensure_ascii=False) + "\nإذا لم تكن هناك أداة مناسبة، اعتذر ولا تختلق استدعاءً.")user = "ما حالة الطقس في القاهرة؟" prompt = ( f"<|im_start|>system\n{system}<|im_end|>\n" f"<|im_start|>user\n{user}<|im_end|>\n" f"<|im_start|>assistant\n")ids = tok(prompt, return_tensors="pt").to(model.device)out = model.generate( **ids, max_new_tokens=256, do_sample=False, repetition_penalty=1.2, eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"),)print(tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True))# Expected: <tool_call>{"name": "get_weather", "arguments": {"location": "القاهرة"}}</tool_call>