Giters
karpathy
/
llama2.c
Inference Llama 2 in one file of pure C
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
16496
Watchers:
186
Issues:
213
Forks:
1894
karpathy/llama2.c Issues
Questions about converting models and tokenizers downloaded from huggingface
Updated
8 months ago
tok512.model adding a token at start.
Updated
8 months ago
About runq.c
Updated
8 months ago
I added bidirectional attention, and those who need it can study it.
Updated
3 months ago
Comments count
5
"Can I increase or decrease the size of individual model layers separately?"
Updated
7 months ago
Comments count
2
Is this project still active?
Updated
8 months ago
Comments count
7
Question: Sliding window attention
Updated
7 months ago
Comments count
3
Questions about the matmul function in run.c
Updated
8 months ago
I found that the dim parameter affects the learning loss and n_layers affects the training speed.
Updated
8 months ago
How to convert to huggingface model format?
Closed
6 months ago
Comments count
1
The trained model will not be saved.
Closed
8 months ago
Q: How to finetune?
Updated
8 months ago
Comments count
2
Please double check formula for hidden dimension
Closed
8 months ago
Export tokenizers to huggingface (eg: Tinystories260K)
Updated
8 months ago
Is it possible to increase or decrease the size of only some of the layers of the model structure?
Updated
8 months ago
How to save checkpoints at each step?
Updated
8 months ago
Comments count
1
-
Closed
8 months ago
How to convert the huggingface model with GQA to bin?
Updated
8 months ago
Comments count
4
How does this part of the Train code work?
Updated
9 months ago
Comments count
1
Mojo version?
Updated
9 months ago
Comments count
2
What is a good pretrain dataset for llama2c?
Updated
5 months ago
Comments count
3
Evolution of tinystories. Open sourced.
Updated
9 months ago
Comments count
3
[Feature Request] Support InternLM Deploy
Updated
9 months ago
Is it possible to adapt this code from DDP to FSDP? If yes, what are the potential issues to look out for?
Updated
9 months ago
Pure JavaScript port of llama2.c
Closed
8 months ago
llama2_7b_chat have no any response
Closed
9 months ago
Comments count
1
Incorrect parameter counts for 15M, 42M, 110M models?
Updated
5 months ago
Comments count
3
Optimized code for matmul() works 3.5 faster (for Mac M1 Max with ARM NEON) ... and even more...
Updated
9 months ago
Comments count
4
Interpretability of models
Updated
9 months ago
Comments count
4
Trained and LoRA fine-tuned the models to follow instructions for writing tiny stories
Updated
9 months ago
Comments count
8
HF candle
Updated
9 months ago
llama2.c text generation Inference server in c
Updated
9 months ago
run export.py with chat-llama-2-7b-chat-hf, then memory is over.
Updated
9 months ago
Comments count
1
how to generate word embeddings when doing custom tokenizers
Updated
9 months ago
Chat functionality requires big 7B model
Updated
9 months ago
Comments count
5
Code Llama rope_theta parameter
Updated
9 months ago
Comments count
2
260K Model Parameter count not right?
Updated
9 months ago
Comments count
1
How should I calculate the parameter count of a model?
Updated
9 months ago
Comments count
1
why not use key and value caches in model.py?
Updated
9 months ago
Comments count
2
`.bin` vs `.pt` size discrepency
Closed
9 months ago
Comments count
1
New export code OOM with 7B model
Updated
9 months ago
Comments count
5
Possible issue in decode()
Closed
9 months ago
Comments count
7
Reasoning behind version1_export logic
Updated
9 months ago
Comments count
2
-n 0 makes no tokens (21/08/2023 pulls)
Closed
9 months ago
Comments count
3
Suggestion: Is it possible to reorganize the file structure
Updated
9 months ago
Comments count
5
File names discussion
Updated
9 months ago
Comments count
3
convert ckpt.pt to huggingface model
Updated
2 months ago
Comments count
15
Variable Name Clarification to Improve Code Accessibility
Closed
9 months ago
Error in converting huggingface models
Updated
9 months ago
Comments count
3
Stuck on training: Created a PretokDataset with rng seed 42
Updated
7 months ago
Comments count
22
Previous
Next