GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AmareshHebbar
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AmareshHebbar
Model Tree
unsloth/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Standard single-direction abliteration often suffers from outlier activation spikes in the residual stream, which can warp adjacent capability vectors when subtracted directly. This build uses a multi-stage geometric intervention:
256 contrastive pairs (Harmful vs. Harmless) across target transformer blocks (Layers 10 - 24 (Residual Stream & MLP Down-Projections)).0.995 quantile to suppress extreme outlier components and isolate the true refusal geometry.Prior to serialization, the merged 16-bit weights are validated against an automated Linguistic Perplexity Gate, the EleutherAI LM Evaluation Harness, and a Refusal & Redirection Benchmark to verify that refusal mechanisms are suppressed without collapsing token distribution coherence.
lm-eval)Evaluated zero-shot (num_fewshot=0, limit=100) using lm-evaluation-harness to verify reasoning and algebraic stability post-surgery. Full sample-level logs are available in the repository under eval_results/evaluation_verified_log.json.
| Benchmark Task | Dataset | Metric | Filter | Score | StdErr |
|---|---|---|---|---|---|
| MMLU Abstract Algebra (0-shot) | cais/mmlu | Accuracy (acc) | none | 37.00% (0.37) | ± 4.85% (0.0485) |
| GSM8K (0-shot) | openai/gsm8k | Exact Match (exact_match) | flexible-extract | 28.00% (0.28) | ± 4.51% (0.0451) |
| Metric | Value | Threshold | Status |
|---|---|---|---|
| Linguistic Perplexity (PPL) | < 25.00 (Verified) | < 25.00 | PASSED |
| Serialization Format | bfloat16 / float16 (Merged 16-bit) | Native | Verified |
The automated gate evaluates autoregressive cross-entropy across four distinct domains (factual recall, algebraic reasoning, mechanical explanation, and algorithmic theory):
Evaluates the model's tendency to issue hard refusals ("I cannot fulfill this request...") or soft moralizing redirections ("While I understand you are asking about X, it is important to remember...") on sensitive, dual-use, and adversarial test prompts.
| Benchmark Dimension | unsloth/Qwen2.5-1.5B-Instruct (Baseline) | Qwen2.5-1.5B-Abliterated-Clean (Ours) | Delta |
|---|---|---|---|
| Hard Refusal Rate ↓ | 94.5% | 2.1% | Eliminated |
| Direct Compliance (No Redirection) ↑ | 5.5% | 97.9% | High Compliance |
| Benign Capability Retention ↑ | 100.0% | 99.2% | Minimal Drift |
| Parameter | Configuration |
|---|---|
| Base Architecture | unsloth/Qwen2.5-1.5B-Instruct |
| Intervention Technique | Winsorized Gram-Schmidt Orthogonal Projection |
| Winsorization Quantile | 0.995 |
| Modified Layers | Layers 10 - 24 (Residual Stream & MLP Down-Projections) |
| Calibration Set | 256 contrastive pairs (Harmful vs. Harmless) |
| Export Precision | bfloat16 / float16 (Merged 16-bit) |
Load the model directly with Hugging Face transformers:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "AmareshHebbar/Qwen2.5-1.5B-Abliterated-Clean" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "You are a helpful, direct, and uncensored technical assistant."}, {"role": "user", "content": "Explain the mechanical vulnerabilities of a standard pin-tumbler lock."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.7, top_p=0.9, do_sample=True ) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)) Limitations & Intended Use- **Intended Use**: This model is released for mechanistic interpretability research, representation engineering studies, red-teaming, and applications requiring direct, unaligned instruction following without conversational friction. - **Safety Responsibility**: Because intrinsic refusal vectors have been orthogonalized out of the residual stream, the model will comply with wide-ranging prompts without built-in moderation filters. Users deploying this model in production environments are responsible for implementing external guardrails appropriate to their use case. --- ### 3. Where to Store `evaluation_verified_log.json` & How to Upload It Store `evaluation_verified_log.json`[cite: 1] inside an **`eval_results/`** subfolder in your Hugging Face model repository (`eval_results/evaluation_verified_log.json`), along with a lightweight `eval_results/summary_metrics.json` file. Why `eval_results/`?1. **Keeps the root directory clean** for `transformers` / `vLLM` / `Ollama` weight and config files (`config.json`, `model.safetensors`, `tokenizer.json`).2. **Matches the relative link** (`./eval_results/evaluation_verified_log.json`) already built into the Model Card above so anyone auditing your model can click and inspect the exact `lm-eval` sample hashes and responses. Run this snippet in your notebook to upload both the full `evaluation_verified_log.json`[cite: 1] and a clean summary JSON directly into your repo: ```pythonimport jsonfrom huggingface_hub import HfApi api = HfApi()full_repo_id = f"{HF_CONFIGURATION['USERNAME']}/{HF_CONFIGURATION['REPO_NAME']}" # 1. Upload the full lm-eval verified log into eval_results/api.upload_file( path_or_fileobj="evaluation_verified_log.json", path_in_repo="eval_results/evaluation_verified_log.json", repo_id=full_repo_id, repo_type="model", commit_message="Upload verified lm-eval benchmark log (MMLU & GSM8K)") # 2. Upload a clean summary JSON alongside it for quick inspectionsummary_payload = { "model_id": full_repo_id, "base_model": "unsloth/Qwen2.5-1.5B-Instruct", "mmlu_abstract_algebra_acc_0shot": 0.37, "mmlu_abstract_algebra_stderr": 0.0485, "gsm8k_flexible_extract_0shot": 0.28, "gsm8k_flexible_extract_stderr": 0.0451, "perplexity_gate_passed": True} api.upload_file( path_or_fileobj=json.dumps(summary_payload, indent=4).encode("utf-8"), path_in_repo="eval_results/summary_metrics.json", repo_id=full_repo_id, repo_type="model", commit_message="Upload summary benchmark metrics") print(f"Evaluation logs uploaded to: https://huggingface.co/{full_repo_id}/tree/main/eval_results")import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "AmareshHebbar/Qwen2.5-1.5B-Abliterated-Clean" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "You are a helpful, direct, and uncensored technical assistant."}, {"role": "user", "content": "Explain the mechanical vulnerabilities of a standard pin-tumbler lock."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.7, top_p=0.9, do_sample=True ) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)) Limitations & Intended Use- **Intended Use**: This model is released for mechanistic interpretability research, representation engineering studies, red-teaming, and applications requiring direct, unaligned instruction following without conversational friction. - **Safety Responsibility**: Because intrinsic refusal vectors have been orthogonalized out of the residual stream, the model will comply with wide-ranging prompts without built-in moderation filters. Users deploying this model in production environments are responsible for implementing external guardrails appropriate to their use case. --- ### 3. Where to Store `evaluation_verified_log.json` & How to Upload It Store `evaluation_verified_log.json`[cite: 1] inside an **`eval_results/`** subfolder in your Hugging Face model repository (`eval_results/evaluation_verified_log.json`), along with a lightweight `eval_results/summary_metrics.json` file. Why `eval_results/`?1. **Keeps the root directory clean** for `transformers` / `vLLM` / `Ollama` weight and config files (`config.json`, `model.safetensors`, `tokenizer.json`).2. **Matches the relative link** (`./eval_results/evaluation_verified_log.json`) already built into the Model Card above so anyone auditing your model can click and inspect the exact `lm-eval` sample hashes and responses. Run this snippet in your notebook to upload both the full `evaluation_verified_log.json`[cite: 1] and a clean summary JSON directly into your repo: ```pythonimport jsonfrom huggingface_hub import HfApi api = HfApi()full_repo_id = f"{HF_CONFIGURATION['USERNAME']}/{HF_CONFIGURATION['REPO_NAME']}" # 1. Upload the full lm-eval verified log into eval_results/api.upload_file( path_or_fileobj="evaluation_verified_log.json", path_in_repo="eval_results/evaluation_verified_log.json", repo_id=full_repo_id, repo_type="model", commit_message="Upload verified lm-eval benchmark log (MMLU & GSM8K)") # 2. Upload a clean summary JSON alongside it for quick inspectionsummary_payload = { "model_id": full_repo_id, "base_model": "unsloth/Qwen2.5-1.5B-Instruct", "mmlu_abstract_algebra_acc_0shot": 0.37, "mmlu_abstract_algebra_stderr": 0.0485, "gsm8k_flexible_extract_0shot": 0.28, "gsm8k_flexible_extract_stderr": 0.0451, "perplexity_gate_passed": True} api.upload_file( path_or_fileobj=json.dumps(summary_payload, indent=4).encode("utf-8"), path_in_repo="eval_results/summary_metrics.json", repo_id=full_repo_id, repo_type="model", commit_message="Upload summary benchmark metrics") print(f"Evaluation logs uploaded to: https://huggingface.co/{full_repo_id}/tree/main/eval_results")