模型:
TheBloke/wizard-mega-13B-GPTQ
任务:
文本生成类库:
Transformers数据集:
anon8231489123/ShareGPT_Vicuna_unfiltered ehartford/wizard_vicuna_70k_unfiltered ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered 3Aehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered 3Aehartford/wizard_vicuna_70k_unfiltered 3Aanon8231489123/ShareGPT_Vicuna_unfiltered语言:
en许可:
otherChat & support: my new Discord server
Want to contribute? TheBloke's Patreon page
这个仓库包含了通过 GPTQ-for-LLaMa 进行4位GPTQ格式量化的模型。
这是使用 GPTQ-for-LLaMa 进行4位量化的结果。
如同正常使用text-generation-webui界面。
wizard-mega-13B-GPTQ-4bit-128g.no-act-order.safetensors
这将与所有版本的GPTQ-for-LLaMa兼容。它具有最大的兼容性。
它是在没有 --act-order 的情况下创建的,以确保与所有UI兼容。
python llama.py /workspace/models/openaccess-ai-collective_wizard-mega-13b c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/wizard-mega-13b/gptq/wizard-mega-13B-GPTQ-4bit-128g.no-act-order.safetensors
欢迎加入我们的Discord进行进一步的支持和关于这些模型和人工智能的讨论:
感谢 chirper.ai 团队!
很多人问我是否可以进行贡献。我喜欢提供模型并帮助人们,非常愿意能够花更多的时间做这些,并扩展到新的项目,如微调/训练。
如果您能够并且愿意进行贡献,我将非常感激,并将帮助我继续提供更多的模型,并开始新的人工智能项目。
捐赠者将优先获取有关人工智能/LLM/模型的所有问题和请求的支持,以及访问私人Discord房间和其他福利。
Patreon特别感谢 : Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
感谢所有慷慨的赞助人和捐赠者!
Wizard Mega是一个Llama 13B模型,经过 ShareGPT , WizardLM 和 Wizard-Vicuna 数据集的精细调整。这些特定的数据集经过筛选,删除了模型回复“作为AI语言模型…”等或拒绝回答的情况。
在第三(最后一个计划的)阶段中,Wizard Mega 13B SFT模型的评估损失增加了。因此,我们初步决定使用第二阶段的检查点作为最终发布候选版本。 https://wandb.ai/wing-lian/vicuna-13b/runs/5uebgm49
Wizard Mega是在8xA100 80GB上使用 Axolotl 构建的,共耗时15小时。此仓库的 /config folder 提供了可以复制此构建的配置。
### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization. ### Assistant: ```python def fib(n): if n < 2: return n elif n in cache: return cache[n] else: a, b = 0, 1 for i in range(2, n+1): cache[i] = a a, b = b, a + b return cache[n] def first_n(n): fib_list = [fib(i) for i in range(n+1)] return fib_list[:n] ``` This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it. The `first_n` function takes an integer `n` as input, and calculates the first n numbers of the Fibonacci sequence using memoization. It returns a list of those numbers.
### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar... ### Assistant: ...and the bartender says "Hey guys, what can I get for you?" The mechanic replies, "I'll have a beer, but make it a quick one. I have to fix this guy's car before he finds out I fiddled with his brakes." The salesman quips, "And I'll have a martini, shaken not stirred. After all, I have to sell this guy a car that doesn't break down on him within the first year of ownership."