GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
frankmorales2020
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
frankmorales2020
Model Tree
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Input Modalities
Output Modalities
Supported Functionality
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.
The governor did not modify them.governor_state.pt, which records the governor configuration
(anchor primes, threshold, cached anchor rows, gate statistics, and a
SHA-256 signature of the prime-indexed embedding rows).VERIFICATION.txt records the run details.The governor evaluates a gate on each training step and pins six
prime-indexed embedding rows ([2, 3, 5, 7, 11, 13]) to their original
values. In the run that produced this repository, the optimizer step was a
no-op (STEP_GATED_NO_MUTATION), so the model was not trained or
fine-tuned.
As a result:
Research and experimentation with the governor tooling. For general use, loading the base model directly is equivalent and avoids downloading a duplicate copy of the weights.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch REPO_ID = "frankmorales2020/deepseek-governed-no-amnesia" tokenizer = AutoTokenizer.from_pretrained(REPO_ID, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( REPO_ID, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)model.eval() prompt = "Explain why prime numbers are important in cryptography."text = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True,)enc = tokenizer(text, return_tensors="pt").to(model.device) out = model.generate( **enc, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.3, no_repeat_ngram_size=3, pad_token_id=tokenizer.eos_token_id,)print(tokenizer.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True))This is a DeepSeek R1 distill (reasoning) model. Feed prompts through the chat template, and expect a
<think> ... </think>reasoning trace before the final answer. To keep only the final answer, split the output on</think>.
python
from huggingface_hub import hf_hub_downloadimport torch state = torch.load( hf_hub_download(REPO_ID, "governor_state.pt"), map_location="cpu", weights_only=False,)print(state["primes"], state["LAMBDA_12"], state["anchor_signature"], state["stats"])Released under the MIT license, inherited from the base model.
Base model: DeepSeek-R1-Distill-Qwen-7B by DeepSeek-AI.
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch REPO_ID = "frankmorales2020/deepseek-governed-no-amnesia" tokenizer = AutoTokenizer.from_pretrained(REPO_ID, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( REPO_ID, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)model.eval() prompt = "Explain why prime numbers are important in cryptography."text = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True,)enc = tokenizer(text, return_tensors="pt").to(model.device) out = model.generate( **enc, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.3, no_repeat_ngram_size=3, pad_token_id=tokenizer.eos_token_id,)print(tokenizer.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True))from huggingface_hub import hf_hub_downloadimport torch state = torch.load( hf_hub_download(REPO_ID, "governor_state.pt"), map_location="cpu", weights_only=False,)print(state["primes"], state["LAMBDA_12"], state["anchor_signature"], state["stats"])