Downloads · 30 days
11
17% of all-time downloads
mimir-qwen3-4b-lora-v1
Bharambe-NL/mimir-qwen3-4b-lora-v1
mimir-qwen3-4b-lora-v1 is a text generation model from Bharambe-NL. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
ℹ️ Use v2 instead. This v1 adapter is kept public for reference and before/after comparison. v2 fixes the primary failure mode — over-eager tool-use on direct-answer questions (Family F: 12 % → 88 % pass rate). ⚠️ Syn…
All-time downloads
65
Public
Repo size
360 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors340 MB · 94%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Apr 18, 2026
- Updated
- Apr 20, 2026
- SHA
- b0429b53
Try a prompt
Base models
Model card
From the Hugging Face model README
Mimir-Qwen3-4B-LoRA v1 (superseded)
ℹ️ Use v2 instead. This v1 adapter is kept public for reference and before/after comparison. v2 fixes the primary failure mode — over-eager tool-use on direct-answer questions (Family F: 12 % → 88 % pass rate).
⚠️ Synthetic / external training data warning (applies to v2; v1 is xLAM-only). Use with expert review for any production legal/regulatory/financial decisions.
LoRA adapter for Qwen/Qwen3.5-4B, fine-tuned as a first-pass tool-calling model for Mimir (a GRC / InfoSec professional knowledge assistant).
Training
- Base:
Qwen/Qwen3.5-4B(bf16) - Method: LoRA (rank 128, alpha 256) — 84.9 M trainable params (1.98 %)
- Data: Salesforce/xlam-function-calling-60k only — 58,716 examples reformatted to Qwen3 chat template
- Hardware: 1× NVIDIA H100 80GB, bf16 + Flash-Attention 2
- Config: 2 epochs, effective batch 64, LR 2e-4 cosine, seq 2048
- Wall time: ~4 hours
Final training metrics (step 1836)
| Metric | Value |
|---|---|
| eval_loss | 0.0659 |
| eval mean_token_accuracy | 98.10 % |
| train_loss | ~0.066 |
70-entry Mimir eval
| Metric | v1 |
|---|---|
| Family F (Should Not Call) pass rate | 1 / 8 (12 %) — primary gap |
| Governance compliance | 68 / 69 (99 %) |
| UNPARSEABLE tool_call JSON | 2 / 70 |
v1 calls tools too aggressively on direct-answer questions. v2 addresses this specifically.
Full reproducibility + eval set: Bharambe-NL/mimir-training.
Usage
Same as v2 — just swap adapter_id = "Bharambe-NL/mimir-qwen3-4b-lora-v1". See the v2 model card for the full loading and generation snippet, including the critical enable_thinking=False and <|im_end|> stop-token settings.
License
Apache-2.0. Base model: Qwen license.
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Apr 18, 2026
- Updated
- Apr 20, 2026