kaiye21/qwen38-27b-sft-ours-633-no-subagent-5ep

text-generation model by kaiye21

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Intermediate checkpoint from SFT step 50/125. 477 training and 23 validation trajectories. Step 50 is the earlier of the two intermediate saves. The adjacent validation losses at steps 45 and 60 were 0.74057 and 0.73963. The lowest observation at step 75 had no checkpoint; step 100 was equally distant. The run used swe-chat-v2-20261102-sft-no-subagent-20261119. The underlying split had 604 training and 29 validation trajectories. The dataset filtering step removed 127 training rows and six validation rows whose main execution trajectories had non-empty subagenttrajectories. The training pipeline retained the authored split of 477 training and 23 validation trajectories. This release provides weights and aggregate training artifacts. The dashed line marks the published checkpoint at step 50. Train loss at that step was 0.77942. The selected checkpoint has no same-step validation measurement. The closest logged point…

kaiye21/qwen38-27b-sft-ours-633-no-subagent-5ep on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T08:13:17.942Z

Inside the original model card — Document outline
  1. Qwen3.8-27B SFT · ours-633-no-subagent
  2. Dataset
  3. Training
  4. Loss curves and checkpoint
  5. MTP

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

kaiye21/qwen38-27b-sft-ours-633-no-subagent-5ep is a text-generation model repository published by kaiye21 on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
text-generation
Library
transformers
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
27,320,697,856
Architecture
Qwen3_5ForCausalLM
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-11-22T06:49:17.000Z
Last modified
2026-11-22T06:56:16.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

openai-community/gpt2

Qwen/Qwen3-0.6B

Qwen/Qwen3-14B

deepseek-ai/DeepSeek-V3.2

Qwen/Qwen2.5-7B-Instruct

Qwen/Qwen3-4B-Instruct-2507