GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aasim-m
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
aasim-m
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
c1899de289a04d12100db370d81485cdf75e47ca.a833e9887bb5e3623c52dc0ce57480784fd77ce6.1e-5; cosine schedule; warmup ratio 0.03; weight decay 0.01; gradient clipping 1.0; seed 42; no sequence packing.| Validation suite | Response-token cross-entropy loss | Evaluated rows / suite rows |
|---|---|---|
| CASS-bench-v2 | 0.1132528484 | 281 / 301 |
| Rodinia | 0.2049942911 | 337 / 349 |
| Unweighted mean of suite losses | 0.1591235697 | — |
Coverage reflects the prepared validation subsets that fit the sequence limit. These suites are used during training for validation and checkpoint selection; they are not an untouched final test set. These are teacher-forced loss measurements, not functional-correctness scores or generated-assembly accuracy. Functional correctness has not been evaluated for this publication.
The checkpoint was checked with Transformers 4.57.1. Install PyTorch and Transformers compatible with your runtime. Use non-thinking mode, matching training, and leave enough room for output within the 32,768-token training limit.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "aasim-m/DAFT-Qwen3-0.6B-checkpoint-4000"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to("cuda").eval()instruction = ("Translate the following NVIDIA GPU assembly function into corresponding AMD GPU assembly. ""Preserve the function's behavior. Return only the translated assembly, without explanations or Markdown fences.")source_assembly = "..." # Replace with a complete NVIDIA assembly function.prompt = tokenizer.apply_chat_template([{"role": "user", "content": instruction + "\n" + source_assembly}],tokenize=False,add_generation_prompt=True,enable_thinking=False,)inputs = tokenizer([prompt], return_tensors="pt").to(model.device)remaining = 32768 - inputs["input_ids"].shape[1]if remaining <= 0:raise ValueError("Input leaves no output space within 32,768 tokens")with torch.inference_mode():output = model.generate(**inputs,max_new_tokens=min(4096, remaining),do_sample=False,use_cache=True,pad_token_id=tokenizer.eos_token_id,)print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
The saved configuration retains its original training settings, including use_cache=false; the example enables caching explicitly for inference. Generated assembly may be incomplete or incorrect and requires downstream validation before execution. This checkpoint has not been evaluated as a general-purpose assistant.
Apache-2.0, following the base model. The included LICENSE is copied from the pinned base-model revision. publication.json records the checkpoint identity, validation metrics, and file hashes. The published weights are unchanged from the local checkpoint.