Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
pathcosmos
/
frankenstallm
like
0
Text Generation
Transformers
Safetensors
GGUF
7 datasets
Korean
English
llama
3b
korean
from-scratch
orpo
instruction-tuned
preference-aligned
fp8
b200
Eval Results (legacy)
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
51
Deploy
Use this model
main
frankenstallm
87.7 GB
Ctrl+K
Ctrl+K
2 contributors
History:
84 commits
pathcosmos
Add Related Projects section with EVAFRILL-Mo links
b9f7777
verified
26 days ago
data
feat: Add SFT training data (filtered, 2.4M samples from 24 sources)
27 days ago
eval
Upload eval/ollama_benchmark_results.json with huggingface_hub (#2)
about 1 month ago
eval_reports
Upload eval_reports/2026-03-09_GGUF_DEPLOYMENT_AND_EVAL_REPORT.md with huggingface_hub (#3)
about 1 month ago
gguf
fix: Replace incorrect 1.2B GGUF with correct 3B ORPO GGUF (Q8_0 3.0GB, byte-fallback)
27 days ago
reports
feat: Add data pipeline scripts + phase reports (Tier 3 - reproducibility)
27 days ago
source
Upload source/PLAN_hybrid_3b_fixes.md with huggingface_hub (#34)
about 1 month ago
.gitattributes
Safe
6.67 kB
feat: Add SFT training data (filtered, 2.4M samples from 24 sources)
27 days ago
README.md
40.4 kB
Add Related Projects section with EVAFRILL-Mo links
26 days ago
config.json
Safe
723 Bytes
fix: Replace incorrect 1.2B config with correct 3B ORPO config (hidden_size=3072, 28 layers, vocab=64256)
27 days ago
generation_config.json
Safe
195 Bytes
fix: Update generation_config.json with correct 3B ORPO byte-fallback tokenizer (vocab=64256)
27 days ago
model.safetensors
6.03 GB
xet
fix: Replace 1.2B model with correct 3B ORPO model (hidden=3072, 28L, vocab=64256, byte-fallback)
27 days ago
sampling_config.json
Safe
981 Bytes
Upload folder using huggingface_hub (#41)
about 1 month ago
tokenizer.json
Safe
4.3 MB
fix: Update tokenizer.json with correct 3B ORPO byte-fallback tokenizer (vocab=64256)
27 days ago
tokenizer.model
Safe
1.42 MB
xet
Upload folder using huggingface_hub (#5)
about 1 month ago
tokenizer_config.json
Safe
44.4 kB
fix: Update tokenizer_config.json with correct 3B ORPO byte-fallback tokenizer (vocab=64256)
27 days ago