foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU)
C++MIT
Issues
- 0
- 8
Tutorial on RAG: Convert fruit vector store failed - GGML_ASSERT: ...... Aborted
#37 opened by GentleYo - 11
- 1
- 1
phi-3.5 moe
#34 opened by ayttop - 5
phi 3.5 moe usage
#31 opened by GlasslessPizza - 1
sparsemixer function in Phi-3.5-MoE-insturct
#33 opened by JustQJ - 1
Phi-3.5-MoE-instruct
#32 opened by ayttop - 1
calculate required scratch memory
#6 opened by foldl - 3
CPU inferencing a lot slower than llama.cpp
#10 opened by netspym - 0
LlaMA 3.1 70B not work
#30 opened by foldl - 2
How to use GPU?
#13 opened by li904775857 - 1
Model id for mistral nemo?
#29 opened by mlsterpr0 - 1
F16 quantization not work
#28 opened by foldl - 3
gemma模型的bug
#26 opened by phpk - 1
baichuan13 does not work well
#27 opened by cagev - 10
bge-reranker is extreamly slow
#24 opened by RobinQu - 3
bindings里面的openai_api.ts好像读不到历史信息
#22 opened by gabrielpondc - 3
The same sentence appears in loop
#19 opened by ChenHuge - 2
你好,请问支持GLM-4V吗?
#23 opened by yhl41001 - 2
crashed using qwen2 72b
#21 opened by cagev - 3
RuntimeError: Internal: could not parse ModelProto from /home/james/glm-4-9b-chat/tokenizer.model
#20 opened by jamfor352 - 1
Does this project have a communication group?
#15 opened by wyrjob - 1
请问可否给个docker镜像
#17 opened by zhanpengjie - 2
quantized InternLM2 failed
#18 opened by cagev - 1
Support GGUF
#16 opened by trufae - 1
build libchatllm error
#14 opened by wzg-zhuo - 1
Compilation of bindings under macOS does not succeed
#12 opened by phpk - 4
- 2
LLM conversion is a issue.
#9 opened by netspym - 5
提供python调用方式
#3 opened by wzg-zhuo - 2
can't build on arm termux
#8 opened by coinight - 1
请问如何部署BCEmbedding的rerank模型?
#7 opened by chenchun0629 - 2
core dumped
#5 opened by MarsMeng1994 - 1
用-p提供命令行的prompt参数时,不支持中文。
#4 opened by yg1988 - 4
how do i run phi-2 on cpu (x86 ec2)
#1 opened by kirilligum