-
2024/03現在gpt3.5-turboより安価かつ
> All Claude 3 models support vision and 200,000 token context windows.
とtoken数も大きいので都合が良い。
xcd0 updated
8 months ago
-
### Details
When creating a "Sweep (fast)" ticket (fast_mode), the ticket count for gpt4 is still being incremented instead of gpt3.5 ticket count. Please fix this bug.
### Files to change
…
-
Talk about King of Glory
-
each customizable item for a task deployment should be configured inside a config file and the frontend should be loaded accordingly
e.g.
```yaml
model:
type: dropdown
items:
- g…
-
The situation is the same for gpt-4 or gpt-4-32k. You can find that the model is not wrong when you log in to poe, but the answer is definitely not gpt4.
-
### 背景
模型提供商openai、Azure、第三方等对模型的调用频次有软性设置。
比如：https://platform.openai.com/account/rate-limits
很多第三方模型提供商，可以提供10w+/秒 的GPT3.5接口请求，从费率上看，又可以放宽GPT3.5的频次。
同时，对GPT4等高消耗Token的模型设置频次限制，也是对终端用户的保护。
#…
-
gpt3 sucks at math and code! I'm trying to use gpt4 for indexing but with no luck. It'd be great if there was a model parameter for indexing commands. currently, it only supports while querying which …
-
Hello, the dataset in the URL you provided, https://github.com/liyucheng09/Selective_Context/releases/download/v0.1.0rc1/datasets_dumps.zip, seems incomplete. There is no data in the news folder, it i…
-
Claude 2.1 api is currently "free", would it be possible to add it as an option and altenative to GPT3.5 / GPT4 ?
Here a link to the API doc:
https://docs.anthropic.com/claude/reference/getting-st…
-
Current we only use OpenAI models to handle it.
Even the cost is relatively low compared to do it manually(for 20,000 documents, roughly 3,000 AUD for GPT3.5, 20,000 for GPT-4)
Still there is privac…