GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CompassioninMachineLearning
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
CompassioninMachineLearning
Model Tree
Qwen/Qwen3-8B-Base
Input Modalities
Output Modalities
Supported Functionality
main contains epoch 2, the best training-time validation checkpoint. Each
completed epoch is independently loadable using its epoch-N revision. Both
training runs stopped after four epochs; there is no epoch-five export.
| Revision | Training step | Training-time validation loss |
|---|---|---|
| epoch-1 | 375 | 1.2472849 |
| epoch-2 | 750 | 1.2268945 |
| epoch-3 | 1125 | 1.2514912 |
| epoch-4 | 1500 | 1.2871689 |
These losses were measured during adapter training, not by a new evaluation of the BF16 exports. Evaluate the four revisions separately to measure behavior changes across epochs.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "CompassioninMachineLearning/Qwen3-8B-Base-CPT-BF16"revision = "main"tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)model = AutoModelForCausalLM.from_pretrained(model_id, revision=revision, dtype=torch.bfloat16, device_map="auto")
Qwen/Qwen3-8B-Base at 49e3418fbbbca6ecbdf9608b4d22e5a407081db4.1586e45fc7c3f7d5e601dc454ba7e15884a2f1df.62933de6ac6e2484a5082afc7d4748c2267368cc7a3331fd874b93f4fe0e609b.embed_tokens and lm_head matrices are included.Training used a 4-bit base; these exports merge the trained adapter into the pinned original BF16 base. The merge was performed using PEFT's safe merge, not Unsloth's export helper. Every tensor was checked for finite BF16 values and the complete architecture's names and shapes. Every epoch passed a standalone load, finite-logit forward pass and short greedy generation. No separate adapter is required, and optimizer/trainer checkpoint files are not included.
merge_manifest.json records source and output checksums. validation.json
records the inference smoke test. training_manifest.json preserves the training
settings. Shard count controls packaging; BF16 specifies the 16-bit precision.