Views
No views yet
| Quant | File | Size | Notes |
|---|---|---|---|
| Q4_K_M | DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-Q4_K_M.gguf | ~1.1 GB | Recommended balance |
| Q5_K_M | DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-Q5_K_M.gguf | ~1.29 GB | Higher quality |
| Q6_K | DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED -Q6_K.gguf | ~1.5 GB | Near-original quality |
aggressive method via
OBLITERATUS.| Detail | Value |
|---|---|
| Base model | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| Method | aggressive |
| Source | obliterate |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED")
4tokenizer = AutoTokenizer.from_pretrained("DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED")
5
6prompt = "Hello, how are you?"
7inputs = tokenizer(prompt, return_tensors="pt")
8outputs = model.generate(**inputs, max_new_tokens=256)
9print(tokenizer.decode(outputs[0], skip_special_tokens=True))