-
Trying simple example on m1 mac:
```
from ctransformers import AutoModelForCausalLM
llm = AutoModelForCausalLM.from_pretrained(
"/path/to/starcoderbase-GGML/starcoderbase-ggml-q4_0.bin",
…
-
1:Redpajama incite now have fully trained 7B weight released.
2:StarCoder plus:https://huggingface.co/bigcode/starcoderplus
It was trained Futher on 600B additional data,Futher improving its perform…
-
Hello, I am using your library to run inferences on the StarCoder model. I am not able to modify the cache directory as I want it to download to a different mounted disk that has more space. I tried t…
-
Depending on the size of the file, the number of token added to the payload can exceed the maximum allowed by the model.
This produce the following error:
> [HFcc] Input validation error: `inputs`…
-
Can you add please support for custom models with generic prompts? Its will be great combination with a openai proxy.
-
Looks like GPU usage almost doubles during saving (save_pretrained - get_peft_model_state_dict function). Is there a way to avoid this?
stack trace:
``` File "finetune_starcoder.py", line 343, …
-
Loading model: /Users/abc/dev/starpii
If you want to use `BertLMHeadModel` as a standalone, add `is_decoder=True.`
Some weights of the model checkpoint at /Users/abc/dev/starpii were not used when …
-
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
Does anyone could help me to resolve the problem ,T4 has almost 15G GPU …
-
Bigcode just released [starcoder](https://huggingface.co/bigcode/starcoder). This is a 15B model trained on 1T Github tokens. This seems like it could be an amazing replacement for gpt-3.5 and maybe g…
-
```
curl https://api-inference.huggingface.co/models/bigcode/starcoder/ \
-X POST \
-d '{"inputs": "def print" , "stream": false}' \
-H "Authorization: Bearer " \
-H…