Get the app
← back to catalog · registered 2026-08-22 13:56

Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only

Raghav-Singhal Llama 100B
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Raghav-Singhal%2Fepe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only"
Response includes
  • classification unknown
  • files 11
  • author_summary 369 models
  • readme_text full
Try next
GET/models?author=Raghav-Singhal
All 369 models by Raghav-Singhal
 GET/models?family=llama&method=unknown
Sibling llama models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
How we label → About ? →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
8
↑ 138% in 90 days
Likes
0
Model age
4mo ago
created 2026-05-27
Downloads over time
Now38→from16↑138%
1523324016 on Jun 1038 on Oct 1238 on Oct 7JunJulAugSepOct
Jun 10 → Oct 12 · 58 snapshots · spans 124 days

Metadata

Tags
transformers safetensors llama text-generation causal-lm bfloat16 conversational text-generation-inference endpoints_compatible region:us

Related

Other by Raghav-Singhal
pbsftmix-cite-safety10-nosys-normal-3b 38 pbsftmix-cite-safety30-nosys-normal-3b 35 pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe 14 normal-smollm-1p7b-100B-20n-2048sl-960gbsz-safelm 13 pbsft-cite-pb-300k-3c-nosys-tok-epe-locuslab-safelm-1p7b 11
Total size
3.19 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-27 20:55
Source huggingface.co/Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only ↗

Files by quantization

Auxiliary files 11 files 3.19 GB
model.safetensors 3.19 GB 858a5ae7 download
tokenizer.json 3.37 MB fe2f520c download
vocab.json 782 KB 0ad5ecc2 download
merges.txt 455 KB 69503b13 download
tokenizer_config.json 11.3 KB 237e73f2 download
special_tokens_map.json 5.77 KB 920b847e download
.gitattributes 1.48 KB a6344aac download
added_tokens.json 937 B 297a3a02 download
README.md 813 B 93fc3c64 download
config.json 667 B e2970751 download
generation_config.json 140 B 26ae32b1 download

README current version from Hugging Face

library_name: transformers
pipeline_tag: text-generation
tags:

  • llama
  • causal-lm
  • bfloat16

epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only

Converted Hugging Face base checkpoint from the Model Raising pretraining run.

Details

  • Architecture: LlamaForCausalLM
  • Base model size: 1.7B
  • Precision on disk: bfloat16
  • Source Megatron checkpoint iteration: 50863
  • Model kind: epe
  • Config vocab size: 49280

Tokenizer

Use the bundled tokenizer from this repository.

This EPE checkpoint uses the extended SmolLM2 tokenizer with <assistant> and 35 <charter_X.Y> tokens. Two named chat templates are available:

Name Assistant turn start
default `<
epe `<

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-05-27Upload epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only HF...a36a152813 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration