-
**The bug**
Updating from guidance==0.1.16 to prerelease guidance==0.2.0rc1 causes model.log_prob() to return 0 rather than the true log probs for a generation when using the llama.cpp backend. I hav…
-
```python
"""
Demonstrates how to use the `ChatInterface` to create a chatbot using
[LangChain Expression Language](https://python.langchain.com/docs/expression_language/) (LCEL)
with streaming an…
-
When running with a llama.cpp model (`from langchain_community.llms import LlamaCpp`) I get
`ValueError: Requested tokens (113654) exceed context window of 4096`
I'm not sure what happens with other…
-
**The bug**
A strings containing certain unicode characters to causes an exception.
Likely because `歪` is a multi-token characters for this tokenizer
```
llama3.engine.tokenizer('歪'.encode('utf8')…
-
## Goal
- Build culture where Eng writes docs (and commits)
## Tasklist
- [ ]
- [ ] Clean up Docs structure
- [ ] Update Swagger API
- [ ] Update CLI
- [ ] cortex.cpp README
- [x] https://gith…
-
I can hard code extras in my dependency like this:
`my_dependency = { path = "../my_dependency", develop = true, extras = ["llamacpp"] }`
What I can't work out is how to pass the extras I want t…
-
Currently when using any chain that has as a llm LlamaCpp and a vector store that was created using a LlamaCppEmbeddings, it requires to have in memory two models (due to how both objects are create…
-
### 🚀 The feature
Update cpp/llamacpp to Llama 3
### Motivation, pitch
Update cpp/llamacpp to Llama 3
### Alternatives
_No response_
### Additional context
_No response_
mreso updated
6 months ago
-
### Jan version
0.5.7
### Describe the Bug
`codestral:22b-v0.1-q3_K_M` works perfectly fine via `ollama` / [Hollama](https://github.com/fmaclen/hollama), but returns "Failed to start" via Jan.ai
#…
-
### Cortex version
v1.0.1
### Describe the Bug
Seems like we don't support MiniCPM V2.6 yet.
Context: https://discordapp.com/channels/1107178041848909847/1299169666987724811/1299216508060303382
…