---
library_name: transformers
tags: []
---

# Nemotron-Diffusion-Exp-Ministral-3B-Instruct

Developed by [DLER team](https://nv-dler.github.io/) @ NVR and will be updated actively. Contact Yonggan Fu and Pavlo Molchanov for any question.


# Environment

Docker path: `/lustre/fsw/portfolios/nvr/users/yongganf/docker/megatron_py25_dllm_ministral.sqsh` on CW-DFW. Apply for interactive nodes with the following command:

```
srun -A {account} --partition interactive --time 4:00:00 --gpus 8 --container-image /lustre/fsw/portfolios/nvr/users/yongganf/docker/megatron_py25_dllm_ministral.sqsh --container-mounts=$HOME:/home,/lustre:/lustre  --pty bash
```

## Chat with Our Model in dLM Mode


```
from transformers import AutoModel, AutoTokenizer
import torch

repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)
model = model.cuda().to(torch.bfloat16)

history = []

user_input = input("User: ").strip()
history.append({"role": "user", "content": user_input})

prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
out_ids, nfe = model.generate(prompt_ids, max_new_tokens=512, steps=512, block_length=32, shift_logits=False, causal_context=True, threshold=0.9, eos_token_id=tokenizer.eos_token_id)

tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
print(f"Model: {tokenized_out}")
print(f"[Num Function Eval (NFE)={nfe}]")
```


## Chat with Our Model in AR Mode


```
from transformers import AutoModel, AutoTokenizer
import torch

repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)
model = model.cuda().to(torch.bfloat16)

history = []

user_input = input("User: ").strip()
history.append({"role": "user", "content": user_input})

prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True, enable_thinking=False)
prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
out_ids, nfe = model.ar_generate(inputs.input_ids, max_new_tokens=512)

tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
print(f"Model: {tokenized_out}")
print(f"[Num Function Eval (NFE)={nfe}]")
```


## Chat with Our Model in Quadratic Self-Speculation Mode

```
from transformers import AutoModel, AutoTokenizer, AutoConfig
import torch

repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)

config = AutoConfig.from_pretrained(repo_name, trust_remote_code=True)
config.enable_self_spec = True

model = AutoModel.from_pretrained(repo_name, config=config, trust_remote_code=True).cuda().to(torch.bfloat16)

history = []

user_input = input("User: ").strip()
history.append({"role": "user", "content": user_input})

prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True, enable_thinking=False)

inputs = tokenizer(prompt, return_tensors="pt")
inputs = inputs.to("cuda")

out_ids, nfe = model.self_spec_generate(inputs.input_ids, max_new_tokens=512, steps=512, block_length=32, ar_mix_weight=0.5, eos_token_id=tokenizer.eos_token_id)

tokenized_out = tokenizer.batch_decode(out_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0]

print(f"Model: {tokenized_out}")
print(f"[Num Function Eval (NFE)={nfe}]")
```

## Chat with Our Model in Linear Self-Speculation Mode

```
from transformers import AutoModel, AutoTokenizer
import torch

repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)
model = model.cuda().to(torch.bfloat16)

history = []

user_input = input("User: ").strip()
history.append({"role": "user", "content": user_input})

prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True, enable_thinking=False)
prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
out_ids, nfe = model.linear_spec_generate(prompt_ids, max_new_tokens=512, block_length=32, eos_token_id=tokenizer.eos_token_id)

tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
print(f"Model: {tokenized_out}")
print(f"[Num Function Eval (NFE)={nfe}]")
```


## Chat with Our Model in Linear Decoding Mode with Multi-Path Verification

```
from transformers import AutoModel, AutoTokenizer
import torch

repo_name = "nvidia/Nemotron-Diffusion-Exp-Ministral-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)
model = model.cuda().to(torch.bfloat16)

history = []

user_input = input("User: ").strip()
history.append({"role": "user", "content": user_input})

prompt = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True, enable_thinking=False)
prompt_ids = tokenizer(prompt, return_tensors='pt').input_ids.to(device='cuda')
out_ids, nfe = model.linear_spec_generate_mp(prompt_ids, max_new_tokens=512, block_length=32, eos_token_id=tokenizer.eos_token_id)

tokenized_out = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
print(f"Model: {tokenized_out}")
print(f"[Num Function Eval (NFE)={nfe}]")
```