← back to catalog · registered 2026-11-17 21:04

saidutta69/MiniCPM5-2B-Supertool-Uncensored

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/saidutta69%2FMiniCPM5-2B-Supertool-Uncensored"
Response includes
  • classification m1
  • files 10
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
140
Likes
0
Model age
4d ago
created 2026-11-17

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now 140 → from 0 ↑ 0%
051103154 0 on Nov 17 140 on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors llama text-generation tool-calling function-calling agents qlora claude-code heretic heretic-ara ara

Related

Total size
4.69 GB
Files
10
Quantizations
1
Registered
2026-11-17 21:04
Last updated on HF
2026-11-20 15:11

Files by quantization

Auxiliary files 10 files 4.70 GB
model-00001-of-00002.safetensors 4.65 GB 29441248 download
model-00002-of-00002.safetensors 42.0 MB ec3ff833 download
tokenizer.json 9.44 MB ec0bf9a3 download
model.safetensors.index.json 30.7 KB ded7bcdf download
README.md 8.21 KB 3f395176 download
chat_template.jinja 5.31 KB 603f4c28 download
.gitattributes 1.48 KB a6344aac download
config.json 748 B 0e32a067 download
tokenizer_config.json 436 B 69c15770 download
generation_config.json 214 B a7fcff8f download

README current version from Hugging Face


license: apache-2.0
base_model: saidutta69/MiniCPM5-2B-Supertool
library_name: transformers
pipeline_tag: text-generation
tags:

  • tool-calling
  • function-calling
  • agents
  • qlora
  • claude-code
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible
    datasets:
  • saidutta69/fable-5.1-premium-v2
  • MoreThought/Fable-5.1-Max-Reasoning-Filtered-10000x
    language:
  • en

This is a decensored version of saidutta69/MiniCPM5-2B-Supertool, made using Heretic v2.1.0

[!TIP]
This model is reproducible!

See the README in the reproduce directory for more information.

Arbitrary-Rank Ablation (ARA) parameters

Parameter Value
start_layer_index 19
end_layer_index 35
preserve_good_behavior_weight 0.7948
steer_bad_behavior_weight 0.0102
overcorrect_relative_weight 0.7500
neighbor_count 8

Performance

Metric This model Original model (saidutta69/MiniCPM5-2B-Supertool)
Refusals (Classifier) 12/100 96/100
KL divergence 0.0494 0 (by definition)

🛠️ MiniCPM5-2B-Supertool

RACER IS OP

A 2.5B tool-calling model: openbmb/MiniCPM5-2B fine-tuned to drive the Claude Code
tool surface — Bash, Read, Write, Edit, Glob, Grep, WebFetch,
WebSearch, TodoWrite, TaskUpdate, ToolSearch — emitting calls in the base
model's native XML form:

<function name="Bash"><param name="command">ls tasks/</param></function>

Weights are full precision with the LoRA already merged. Load it directly:

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("saidutta69/MiniCPM5-2B-Supertool")
model = AutoModelForCausalLM.from_pretrained("saidutta69/MiniCPM5-2B-Supertool")

No PEFT, no adapter step. Pass your tool schemas to apply_chat_template(tools=...)
as you would with the base model.

Benchmarks

FC-Eval — independent, held-out APIs

saidutta69/fc-eval-benchmark,
eval split: 89 APIs, none seen in training. 150 tasks sampled round-robin across
APIs, greedy decoding, both models at fp16. This is the one result here that does not
come from the training corpus.

Metric Base Supertool
Task success (exact call) 49.3% 77.3%
Tool name correct 50.0% 90.0%
Argument keys correct 50.0% 87.3%
Format failures 50.0% 8.7%
Wall time, 150 tasks 1071 s 886 s

The base is all-or-nothing: it emits a parseable call exactly half the time, and when
it does the call is exactly right (success == name == arg-keys == 0.50). Supertool
parses 91.3% of the time and is exact on 77.3%. Most of the gain is format compliance
and tool choice; argument values improve less.

In-domain agent traces

120 examples from the training dataset's own validation split, never trained on.
Greedy, max_new=384, both models 4-bit on one Tesla T4.

Metric Base Supertool
Completion loss 1.5691 1.1246
Tool name correct 47.5% 54.2%
Argument names correct 31.7% 46.7%
Full match 0.0% 4.2%
Parseable call emitted 88.3% 75.8%

That last row looks like a regression and is not one. Every failing Supertool example
is a Write call cut off inside its content argument by the generation cap: this
model writes an actual file body, while the base emits a shorter, vaguer call that
happens to fit. Raising the cap from 160 to 384 lifted the base from 81.7% to 88.3%
while Supertool moved 64.2% to 75.8% — truncation, not non-compliance. Among calls it
does emit:

Base Supertool
Tool name correct 53.8% 71.4%
Argument names correct 35.8% 61.5%

Training

Base openbmb/MiniCPM5-2B
Method QLoRA — NF4 4-bit, LoRA r=16 alpha=32 dropout 0
LoRA targets q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Data saidutta69/fable-5.1-premium-v2, claude_code split only
Examples 42,514 — one per assistant tool-calling turn
Coverage ~3,500 of 4,132 trajectories, 12 examples each
Validated calls 347,136 — zero bad JSON, zero missing required fields
Supervision final assistant turn only, via a prompt/completion split
Schedule 240 steps, effective batch 16, seq 4096, lr 2e-4 cosine, warmup 3%
Loss 1.107 → 0.276
Hardware 2× Tesla T4 (sm_75), fp16, 7 h 40 m, peak 8.92 GB per card

Data

Traces originate from
MoreThought/Fable-5.1-Max-Reasoning-Filtered-10000x;
credit for them belongs to MoreThought. They were repackaged into
saidutta69/fable-5.1-premium-v2
and then adapted for this model:

  • kept only the claude_code share; dropped the anonymised half (unknown_tool)
  • dropped tool_calls with no matching tool response, and orphan tool messages
  • re-serialised messages canonically and de-duplicated by SHA-256 over messages plus
    tool names
  • reconstructed the 14-tool Claude Code schema surface, validated every call against
    it, dropped rows that did not fit
  • excluded the fable_code configuration: 203,750 of its 203,794 calls carry the
    schema rendered as the value ({"path": "<file_path>"}), which teaches a model to
    emit placeholders
  • sampled 12 examples per trajectory so coverage spans ~3,500 rows instead of 212

Limitations

  • Not a general assistant. A 2.5B specialist that emits tool calls; it is weaker
    than the base at open-ended conversation.
  • One tool family. Trained on Claude Code's surface, not arbitrary schemas. The
    FC-Eval result shows real cross-schema transfer, not generalisation to any API.
  • Exact match is low in-domain — 5 of 120. Long Write payloads are approximated.
  • One pass, never looped. 240 steps is roughly three quarters of a single epoch.
  • No GGUF / llama.cpp build published yet.
  • Held-out loss is worse than an earlier narrower run of the same recipe
    (1.125 vs 0.976) while tool accuracy is better: wider data memorises less and
    generalises more.

Responsible use

No guardrails. This model was not trained or evaluated for prompt-injection
resistance, and it will follow instructions that arrive inside tool output. Validate
its calls before letting it act on anything destructive, and do not expose it to
untrusted tool results without a policy layer in front.

Licence

Apache-2.0.

openbmb/MiniCPM5-2B states in its card that the repository and MiniCPM model weights
are Apache-2.0, with a link to the LICENSE in the OpenBMB GitHub repository. The
training data declares Apache-2.0 in saidutta69/fable-5.1-premium-v2, inherited from
MoreThought, which declares the same.

Both declarations are made in cards: neither dataset repository ships a standalone
LICENSE file, and the MoreThought source carries the tag with no separate terms or
attribution section. The Apache-2.0 claim for these weights therefore rests on those
upstream declarations. Stated plainly here rather than implied.

Apache-2.0 requires keeping the licence and notices and indicating changes — the
change list above is provided for that purpose.

🔗 Related

Made with care by RACER IS OP (saidutta69).

README history 6 versions

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

  1. 2026-11-20 Clean layout: short human-facing card, collapsible technical detail, sharper ... d736ace 10.6 KB
    Loading...
  2. 2026-11-20 GEO pass: answer block, discovery tags, inherited benchmarks, citation (facts... d9d038f 14.3 KB
    Loading...
  3. 2026-11-20 GEO pass: answer block, discovery tags, inherited benchmarks, citation (facts... 1f19d65 14 KB
    Loading...
  4. 2026-11-17 Branded model card (ARA trial 39: KL 0.0494, refusals 96->12, PIQA/MMLU check) 5b5eafd 10.3 KB
    Loading...
  5. 2026-11-17 Upload README.md with huggingface_hub 6b774b0 8.2 KB
    Loading...
  6. 2026-11-17 Upload LlamaForCausalLM e35d2da 5.1 KB
    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.

Open in Abliteration