-
Hi, thanks for your awesome work. I am very interested in your work but facing problems when reproducing the gsm8k result.
I keep github code unchanged and run original shell script , and get:
```…
-
I got this error message while trying to run the prompt in the README file
File "python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 402, in forward
kv_seq_len += past_key…
-
Hello,
I am having problems installing Llama2. I am trying to install it on Windows and I am stuck on the step where you run:
`pip install -r requirements.txt `
**_Note: I made sure to have CM…
-
用户在通过Llama2-7b模型验证DeeLink能力时遇到问题，以下为原话。
---------------------邮件原文---------------------
目前正在通过Llama2-7b模型验证DeeLink能力，其中遇到两个问题需要求助下：
1. 在昇腾上通过DeepLink训练Llama2-7b，验证无代码改动可在英伟达与昇腾无障碍训练。我使用的llama2-chine…
-
I met this issue when fine-tuning the LLaMa-7B-Chat-hf with example dataset:
Traceback (most recent call last):
File "finetune-lora.py", line 656, in
train()
File "finetune-lora.py", li…
-
chat with multiple model available with @
for example:
1. setup : above chat box rather than pick 1 model able to pick group model (group model set in the setting)
2. use: type prompt in prompt bo…
-
# Top level issue for LLM matmul optimizations
### Llama2
#### Repro
branch: cglagovich/6689
```
./tt_metal/tools/profiler/profile_this.py -c "pytest -svv models/demos/llama2_70b/tests/pe…
-
### 🐛 Describe the bug
We have an Android CI job to run llama2 demo app on actual S22 devices with stories model on OSS CI at https://github.com/pytorch/executorch/blob/main/.github/workflows/android…
-
While creating the RetrievalQA, it shows this error of not being able to instantiate abstract class BaseRetriever with abstract methods _aget_relevant_documents, _get_relevant_documents. The error can…
-
when run: ./finetune_lora.sh,
got: TypeError: Object of type Tensor is not JSON serializable .
detail:
Traceback (most recent call last):
File "/home/david/qw/Llama2-Chinese0/train/sft/fine…