Hugging Face's logo

Verdugie
/
STEM-Oracle

Text Generation
GGUF
English
qwen3_5_text
27b
stem
tutor
math
physics
chemistry
biology
computer-science
claude-distillation
conversational
local
offline
lm-studio
llama-cpp
Model card Files
xet
 Community
1
Verdugie commited on
Commit
9a82763
·
1 Parent(s): 4b89c98

Add architecture spec paper link in Dataset section

Browse files
Files changed (7) hide show
  1. .gitattributes +0 -38
  2. README.md +3 -1
  3. STEM-Oracle-27B-Q4_K_M.gguf +0 -3
  4. STEM-Oracle-27B-Q6_K.gguf +0 -3
  5. STEM-Oracle-27B-Q8_0.gguf +0 -3
  6. eval/training_metadata.json +0 -14
  7. training-data/opus-candid-v35-27b.json +0 -0
.gitattributes DELETED
@@ -1,38 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- STEM-Oracle-27B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
- STEM-Oracle-27B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
38
- STEM-Oracle-27B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md CHANGED
@@ -238,9 +238,11 @@ The Opus Candid models are built for personality and conversation. STEM-Oracle i
238
 
239
  Training data will be available at [Verdugie/opus-candid-training-data](https://huggingface.co/datasets/Verdugie/opus-candid-training-data). ShareGPT format, Apache 2.0, compatible with TRL, Axolotl, and LLaMA-Factory.
240
 
 
 
241
  **License:** Apache 2.0. Open weight. No guardrails.
242
 
243
  ---
244
 
245
  *Built by [Saul Verdugo](https://huggingface.co/Verdugie) — independent ML researcher. OpusReasoning@proton.me*
246
- <!-- build: 2026-03-10 18:33 -->
 
238
 
239
  Training data will be available at [Verdugie/opus-candid-training-data](https://huggingface.co/datasets/Verdugie/opus-candid-training-data). ShareGPT format, Apache 2.0, compatible with TRL, Axolotl, and LLaMA-Factory.
240
 
241
+ For the full training architecture methodology: [V3.5 Architecture Spec](https://huggingface.co/datasets/Verdugie/opus-candid-training-data/blob/main/papers/Opus-Candid-V3.5-STEM-Oracle-Architecture-Spec.docx).
242
+
243
  **License:** Apache 2.0. Open weight. No guardrails.
244
 
245
  ---
246
 
247
  *Built by [Saul Verdugo](https://huggingface.co/Verdugie) — independent ML researcher. OpusReasoning@proton.me*
248
+ <!-- build: 2026-03-10 19:07 -->
STEM-Oracle-27B-Q4_K_M.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d68575c439413e711bc3d879caf790560e48ec52fe9cf421cc4b8b31c03dabfb
3
- size 16545665088
 
 
 
 
STEM-Oracle-27B-Q6_K.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:80514e56d22500f6460bb8f8e631bb897a8d235645a79822589163152f8d5ad5
3
- size 22080473952
 
 
 
 
STEM-Oracle-27B-Q8_0.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcaeb114456406c7d4e81fbbc76fef261353ace981edfb1d6f226c9f8bcdc62e
3
- size 28593105184
 
 
 
 
eval/training_metadata.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "model": "Qwen/Qwen3.5-27B",
3
- "mode": "bf16 LoRA",
4
- "lora_r": 128,
5
- "lora_alpha": 256,
6
- "epochs": 3,
7
- "learning_rate": 5e-05,
8
- "final_loss": 0.49208340033459563,
9
- "train_time": "15:31:27",
10
- "dataset_size": 5179,
11
- "gpu": "NVIDIA A100-SXM4-80GB",
12
- "vram_gb": 79.249755859375,
13
- "timestamp": "2026-03-10T22:29:22.371059"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training-data/opus-candid-v35-27b.json DELETED
The diff for this file is too large to render. See raw diff