Downloads · 30 days
19
21% of all-time downloads
swesmith_8b-step35
laion/swesmith_8b-step35
swesmith_8b-step35 is a text generation model from laion. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
RL-trained Qwen3-8B on SWEsmith tasks (32k context, no rope scaling, 35 steps).
All-time downloads
89
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 18, 2026
- Updated
- Mar 18, 2026
- SHA
- ba67d8bf
Try a prompt
Base models
Model card
From the Hugging Face model README
swesmith_8b-step35
RL-trained Qwen3-8B on SWEsmith tasks (32k context, no rope scaling, 35 steps).
Training Details
| Parameter | Value |
|---|---|
| Base model | laion/r2egym-nl2bash-stack-bugsseq-fixthink-again (Qwen3-8B SFT) |
| Dataset | SWEsmith oracle-verified (2,500 tasks, 120s timeout) |
| Algorithm | RLOO-N (Leave-One-Out with neutral masking) |
| Learning rate | 2.0e-5 |
| Train batch size | 32 |
| Samples per prompt | 8 |
| Max episodes | 64 |
| Max generate length | 8,192 tokens |
| Max input tokens | 24,000 |
| Max model length | 32,768 |
| Rope scaling | None (32k native context) |
| KL loss | Disabled |
| Reward shaping | Enabled (pass_ratio) |
| Staleness steps | 16 |
| Policy nodes | 2 (8 GPUs, FSDP2) |
| Inference engines | 20 (TP=1) |
| Training steps | 35 |
| Framework | BenSkyRL + Harbor |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("laion/swesmith_8b-step35")
tokenizer = AutoTokenizer.from_pretrained("laion/swesmith_8b-step35")
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Mar 18, 2026
- Updated
- Mar 18, 2026