Downloads · 30 days
2
7% of all-time downloads
ps4mas-sft-mt-glm52-9b-v2
yinita/ps4mas-sft-mt-glm52-9b-v2
ps4mas-sft-mt-glm52-9b-v2 is a machine learning model from yinita. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
LoRA SFT on Qwen/Qwen3.5-9B with strict messagelossmask over glm52 multitrack v2: sft2acquire (importance top-3 keys only, empty-content acquireuserinfo) + sft3finalbalanced (composite≥3, upsampled), history tool name…
All-time downloads
30
Public
Repo size
136 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors116 MB · 85%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026
- SHA
- 6a74a20d
Base models
Model card
From the Hugging Face model README
ps4mas-sft-mt-glm52-9b-v2
LoRA SFT on Qwen/Qwen3.5-9B with strict message_loss_mask over glm52 multitrack v2:
sft2_acquire (importance top-3 keys only, empty-content acquire_user_info) +
sft3_final_balanced (composite≥3, upsampled), history tool names canonicalized
(acquire_user_info / query_memory).
| Data | data/sft_splits/glm52_multitrack/sft_masked_train.jsonl (7232 rows) |
| Method | LoRA r=16 α=32, masked SFT |
| Epochs / lr | 3 / 1e-4 |
| Seq | 4096 |
Local path: results/0903/sft_mt_glm52_9b_v2
Uploaded: 2026-09-04T17:13:32.115358+00:00
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B", trust_remote_code=True)
model = PeftModel.from_pretrained(base, "yinita/ps4mas-sft-mt-glm52-9b-v2")
tok = AutoTokenizer.from_pretrained("yinita/ps4mas-sft-mt-glm52-9b-v2", trust_remote_code=True)
- Library
- peft
- License
- apache-2.0
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026