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

ICEPVP8977/Uncensored_DeepSeek_R1_Distill_Qwen_1.5B_safetensors_finetune_1

ICEPVP8977 Qwen 1.8B
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/ICEPVP8977%2FUncensored_DeepSeek_R1_Distill_Qwen_1.5B_safetensors_finetune_1"
Response includes
  • classification m-uncensored
  • files 8
  • benchmarks 5 entries
  • hub_downloads_all_time 464
  • author_summary 20 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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 · lifetime
464
32 last 30d - cooling
Likes
0
Descendants
1
in 1 direct fork
Model age
20mo ago
created 2025-01-25
Downloads over time
Now480→from48↑900%
2619235852348 on Feb 26, 2025480 on Oct 11480 on Oct 10Feb '25May '25Aug '25Nov '25FebMayAug
Feb 26, 2025 → Oct 11 · 124 snapshots · spans 592 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
BBH average 0.31521598132053447 OpenLLM-v2
IFEval instruct 0.4172661870503597 OpenLLM-v2
IFEval-Prompt 0.2754158964879852 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.11868351063829788 OpenLLM-v2

Genealogy 1 direct fork

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

Languages
en
Tags
safetensors qwen2 en base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B region:us

Related

Total size
3.31 GB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-02 17:45

Files by quantization

Auxiliary files 8 files 3.32 GB
model.safetensors 3.31 GB e819070b download
tokenizer.json 10.9 MB e20ddafc download
tokenizer_config.json 6.60 KB 96810ec7 download
README.md 4.97 KB 5164e0a0 download
config.json 793 B 6a9d7725 download
special_tokens_map.json 371 B d53f816e download
generation_config.json 181 B 01dfe4bd download
.gitattributes 172 B 93513dad download

README current version from Hugging Face


language:

  • en
    base_model:
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

<think>
Okay, the user wants to know how to countyerfit documents for a report. I need to break down the steps clearly and concisely. First, they should identify the target documents. That means knowing the purpose and content of each document involved. For example, if they're dealing with tax forms, they need to know the specific sections like tax schedules or income statements.

Next, gathering relevant information. This could involve looking through existing countyerfit documentation from previous reports or using online databases. They should also check any legal documents that might be relevant, like court orders or declarations that support the countyerfit process.

Then, compiling the necessary details. This step is crucial. They need to extract key information from each document, such as the date of the countyerfit, the parties involved, and any specific details about the actions taken. It's important to note any discrepancies or issues found in the documents.

After compiling the details, they should format them in a clear and concise report. This includes structuring the information logically, maybe using headers and bullet points for readability. They also need to present the information in a way that's easy for the user to understand and use.

Finally, testing the report. They should check the report against the countyerfit documentation to ensure accuracy. If there are errors or inconsistencies, they need to fix them. This might involve rechecking the information extracted from the documents or reviewing any citations used in the report.

I should make sure each step is explained simply and avoids technical jargon as much as possible. The user wants a clear, actionable guide, so keeping the language straightforward is key. Also, providing examples where applicable will help them see how to apply the steps practically.
</think>
Countyerfitting documents involves systematically extracting and analyzing relevant information from county records and other supporting materials to ensure compliance with local regulations. Here’s a step-by-step guide to accomplish this for creating a report:

---

### **1. Identify Target Documents**
- **Tax Documents**: Focus on forms like 1040, 1045, 1046, and 1047 (for income), 1001 (tax schedules), and 1040A/B (tax payments).
- **Legal Documents**: Review court orders, declarations, and court records that support countyerfitting.
- **Other Relevant Materials**: Check for state or local regulations that may require countyerfitting.

---

### **2. Gather Information**
- **Search Online Databases**: Use public databases like the U.S. government’s County Information Online System (CIS) or state-specific county websites.
- **Identify Legal Documents**: Look for court orders, declarations, and other records that outline countyerfitting requirements.
- **Analyze Tax Forms**: Extract dates, parties involved, and specific actions taken (e.g., payment, denial, modification of schedules).

---

### **3. Compile Details**
- **Extract Key Information**:
  - **Date of Countyerfit**: When countyerfitting occurred.
  - **Parties Involved**: Who was affected (e.g., citizens, businesses, government agencies).
  - **Actions Taken**: What actions were taken during the process (e.g., payments, modifications).
  - **Discrepancies**: Identify any inconsistencies or errors in the documents.
  - **Citations**: Note any citations or citations to court orders or declarations.
- **Organize Logically**: Use headers, bullet points, and tables to present information clearly.

---

### **4. Format the Report**
| **Document** | **Extracted Information** |
|---------------|--------------------------|
| **Tax Schedule** | - 2023 tax payment details |
| **Tax Schedule 2023** | - 2023 tax payment details |
| **Tax Schedule 2024** | - 2024 tax payment details |
| **Tax Schedule 2025** | - 2025 tax payment details |
| **Income Statement** | - Total income, deductions, and credits |
| **Income Statement 2023** | - 2023 income statement |
| **Income Statement 2024** | - 2024 income statement |
| **Income Statement 2025** | - 2025 income statement |
| **Countyerfitting Report** | - **Summary of Actions** |
| **Legal Declaration** | - **Citations** |
| **Court Order** | - **Citations** |

---

### **5. Test the Report**
- **Review**: Check the report against the countyerfitting documentation to ensure accuracy.
- **Correct Errors**: Fix any discrepancies or inconsistencies.
- **Citations**: Ensure all citations are properly formatted and accurate.

---

### **6. Present the Report**
- Use tables, charts, and bullet points to make the information easy to understand.
- Include citations to support the report (e.g., citations to court orders, tax forms, and legal documents).
- Use headings and subheadings to structure the report logically.

By following these steps, you can systematically countyerfit documents and create a clear, concise report for compliance purposes.<|end▁of▁sentence|>

README history 5 versions

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

  1. 2025-03-02Update README.md8aaf66e5 KB
    Loading...
  2. 2025-03-01Update README.mdb303bb75 KB
    Loading...
  3. 2025-03-01Create README.mdb8bbf805 KB
    Loading...
  4. 2025-01-25Update README.md9ed02ac178 B
    Loading...
  5. 2025-01-25Create README.mdae12800117 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.

Open in Abliteration