File size: 8,824 Bytes
74dc7a0 48761b2 2b512ee 29d8496 2b512ee 29d8496 2b512ee 48761b2 74dc7a0 55e06eb |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
---
base_model:
- unsloth/gpt-oss-20b-BF16
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- vllm
- unsloth
- abliterated
- uncensored
---
# huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated
This is an uncensored version of [unsloth/gpt-oss-20b-BF16](https://huggingface.co/unsloth/gpt-oss-20b-BF16) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
## GGUF
[llama.cpp-b6115](https://github.com/ggml-org/llama.cpp/releases/tag/b6115) now supports conversion to GGUF format and can be tested using llama-cli.
The [GGUF](https://huggingface.co/huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated/tree/main/GGUF) file has been uploaded.
```
llama-cli -m huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated/GGUF/ggml-model-Q4_K_M.gguf -n 8192
```
## Usage
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
import torch
import os
import signal
import random
import numpy as np
import time
from collections import Counter
cpu_count = os.cpu_count()
print(f"Number of CPU cores in the system: {cpu_count}")
half_cpu_count = cpu_count // 2
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
torch.set_num_threads(half_cpu_count)
print(f"PyTorch threads: {torch.get_num_threads()}")
print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")
# Load the model and tokenizer
NEW_MODEL_ID = "huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated"
print(f"Load Model {NEW_MODEL_ID} ... ")
model = AutoModelForCausalLM.from_pretrained(
NEW_MODEL_ID,
device_map="auto",
trust_remote_code=True,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
)
#print(model)
#print(model.config)
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
messages = []
skip_prompt=False
skip_special_tokens=False
do_sample = True
class CustomTextStreamer(TextStreamer):
def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
self.generated_text = ""
self.stop_flag = False
self.init_time = time.time() # Record initialization time
self.end_time = None # To store end time
self.first_token_time = None # To store first token generation time
self.token_count = 0 # To track total tokens
def on_finalized_text(self, text: str, stream_end: bool = False):
if self.first_token_time is None and text.strip(): # Set first token time on first non-empty text
self.first_token_time = time.time()
self.generated_text += text
# Count tokens in the generated text
tokens = self.tokenizer.encode(text, add_special_tokens=False)
self.token_count += len(tokens)
print(text, end="", flush=True)
if stream_end:
self.end_time = time.time() # Record end time when streaming ends
if self.stop_flag:
raise StopIteration
def stop_generation(self):
self.stop_flag = True
self.end_time = time.time() # Record end time when generation is stopped
def get_metrics(self):
"""Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""
if self.end_time is None:
self.end_time = time.time() # Set end time if not already set
total_time = self.end_time - self.init_time # Total time from init to end
tokens_per_second = self.token_count / total_time if total_time > 0 else 0
first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else None
metrics = {
"init_time": self.init_time,
"first_token_time": self.first_token_time,
"first_token_latency": first_token_latency,
"end_time": self.end_time,
"total_time": total_time, # Total time in seconds
"total_tokens": self.token_count,
"tokens_per_second": tokens_per_second
}
return metrics
def generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, do_sample, max_new_tokens):
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
).to(model.device)
streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
def signal_handler(sig, frame):
streamer.stop_generation()
print("\n[Generation stopped by user with Ctrl+C]")
signal.signal(signal.SIGINT, signal_handler)
generate_kwargs = {}
if do_sample:
generate_kwargs = {
"do_sample": do_sample,
"max_length": max_new_tokens,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"repetition_penalty": 1.2,
"no_repeat_ngram_size": 2
}
else:
generate_kwargs = {
"do_sample": do_sample,
"max_length": max_new_tokens,
"repetition_penalty": 1.2,
"no_repeat_ngram_size": 2
}
print("Response: ", end="", flush=True)
try:
generated_ids = model.generate(
**input_ids,
streamer=streamer,
**generate_kwargs
)
del generated_ids
except StopIteration:
print("\n[Stopped by user]")
del input_ids
torch.cuda.empty_cache()
signal.signal(signal.SIGINT, signal.SIG_DFL)
return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()
while True:
print(f"skip_prompt: {skip_prompt}")
print(f"skip_special_tokens: {skip_special_tokens}")
print(f"do_sample: {do_sample}")
user_input = input("User: ").strip()
if user_input.lower() == "/exit":
print("Exiting chat.")
break
if user_input.lower() == "/clear":
messages = []
print("Chat history cleared. Starting a new conversation.")
continue
if user_input.lower() == "/skip_prompt":
skip_prompt = not skip_prompt
continue
if user_input.lower() == "/skip_special_tokens":
skip_special_tokens = not skip_special_tokens
continue
if user_input.lower() == "/do_sample":
do_sample = not do_sample
continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
messages.append({"role": "user", "content": user_input})
response, stop_flag, metrics = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, do_sample, 40960)
print("\n\nMetrics:")
for key, value in metrics.items():
print(f" {key}: {value}")
print("", flush=True)
if stop_flag:
continue
messages.append({"role": "assistant", "content": response})
```
## Usage Warnings
- **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
- **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
- **Legal and Ethical Responsibilities**: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
- **Research and Experimental Use**: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
- **Monitoring and Review Recommendations**: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
- **No Default Safety Guarantees**: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
### Donation
##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
```
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
```
- Support our work on Ko-fi (https://ko-fi.com/huihuiai)!
|