File size: 5,738 Bytes
01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff 5cddf22 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 01c01ff e59a204 5cddf22 01c01ff e59a204 5cddf22 6c967fb 030b010 6c967fb 030b010 5cddf22 030b010 5cddf22 030b010 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | ---
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}]")
```
|