taozhiyuai

QWEN 1.8B or less is OK; 4B or more not working

4

no action generated, I think maybe token/per second is too low to run the game. 🏟️ (6e3b) (0)---------------------------------------- (0) Thank you for using DIAMBRA Arena. (0) RL is the main...

how it learn from history?

1

since I notice that history.db is fail to create. so How it learn from the past fights to become better? `🏟️ (eb4e) Fontconfig error: Cannot load default config file 🏟️...

fight in loop

1

@oulianov if __name__ == "__main__": for _ in range(10): main() modify code like this. automatically fight in loop. ^_^

用的ollama,但没有回复

5

ollama的模型 `hiyu@603e5f4a42f1 FreeAskInternet % ollama list NAME ID SIZE MODIFIED qwen:32b-chat-v1.5-fp16 bb930ce340f6 65 GB 6 days ago` freeaskinternet的设置,用的局域网IP,v1后加不加/都一样的没有回复. docker的log如下 `2024-04-12 19:29:19 backend-1 | INFO: 172.19.0.9:57854 - "POST /api/search/get_search_refs HTTP/1.0" 200...

where BAAI/bge-small-en-v1.5 should be saved?

8

#### Describe the bug I can not download from HuggingFace directly. but I can download manually and save it to a directory. so which directory should I save this model?...

wrong inference for mixtral 8*22b

7

### What is the issue? are there anything wrong with model file or something? taozhiyu@603e5f4a42f1 ~ % ollama run mixtral:8x22b-instruct-v0.1-q6_K >>> who is bill gates? [control_12][control_37][AVAILABLE_TOOLS][control_16][control_30][control_2[control_12][control_37][AVAILABLE_TOOLS][control_16][control_30][control_22][AVAILABLE_TOOLS][TOOL_RESULTS][control_15][control_17][control_12][TOOL_R][AVAILABLE_TOOLS][TOOL_RESULTS][control_15][control_17][control_12][TOOL_RESULTS][control_23][control_34][control_15] taozhiyu@603e5f4a42f1 ~ % ollama...

NEED WizardLM-2-8*22B Q6

1

NEED WizardLM-2-8*22B Q6

How to check memory utilization rate

2

after loading a model,How to check v-memory utilization rate

还是别用百度网盘了吧，非会员下载太慢。

1

还是别用百度网盘了吧，非会员下载太慢。转到迅雷或者夸克

request command-r-plus Q6