-
What is best practice to Quantize a common 16Bit 70B Model on a single A100 VM?
What code do you use when you have a 70B e.g. Unsloth fine-tuned model (merged Adapter)?
With the default code I get…
-
### Description
Been doing test with tools now that it's working as expected. No issues with OpenAI.
But the same request now with Gemini return a very long and convoluted error that I am unsure w…
-
When I try to run short prompts (up to ~200 tokens) everything works well, however, if I increase the number of tokens in the input I get the following error:
```
Output: 2024-06-03 08:12:09.7100776…
-
**Background**
We see many people struggling with the CV AI generation from different angles: not clear instructions, AI has a limit of trying, and acceptance criteria aren't clear for volunteers.
**…
-
Create a TerraForm stack that allows to deploy GenAI examples on Google Cloud using a single node Docker Compose. The template should take an argument of which sample to deploy, setup all the necessar…
-
```python
load_dotenv()
api_key = os.getenv("GENAI_API_KEY")
if not api_key:
api_key = st.secrets["GENAI_API_KEY"]
if not api_key:
st.er…
-
### Describe the issue
We have converted the translation LLM 7B model to ONNX format using Optimum Hugging Face and then quantized it to 8-bit quantization with Dynamic quantization technique. Ho…
-
**Is your feature request related to a problem?**
We need to support a connector to the Oracle Cloud Infrastructure (OCI) and OCI GenAI service as ML so that the conversation search can work for Orac…
-
**Kibana version:**
main/8.9
**Elasticsearch version:**
main/8.9
**Original install method (e.g. download page, yum, from source, etc.):**
Run es from snapshot and kibana locally
**Descr…
-
We are getting error after getting response from gemini.
Error: "The `response.text` quick accessor only works for simple (single-`Part`) text responses. This response is not simple text.Use the `r…