ml-explore mlx-examples issues

ml-explore / mlx-examples

Examples in the MLX framework

MIT License

5.49k stars 790 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Model type deepseek_v2 not supported.

#859 NotYourName24 opened 1 day ago
1
support for Gemma 2

#858 Rehan-shah closed 1 day ago
1
Add logit soft capping to gemma, and fix precision issues

#857 N8python opened 1 day ago
10
Add recurrent gemma

#856 awni opened 3 days ago
0
gemma2

#855 awni closed 3 days ago
3
Received parameters not in model: {extras}.

#854 Gloriashield closed 4 days ago
1
Example of response generation with optional arguments

#853 a-wozniakowski opened 4 days ago
0
Fix streaming SPM decoder for Yi

#852 awni closed 4 days ago
1
Server loads the model on demand from the request

#851 angeloskath closed 3 days ago
0
NameError: name 'resume_adapter_file' is not defined

#850 rainrain1230 closed 5 days ago
1
Discrepancies in generations from the fine tuned models after and before converting them into GGUF. The output generations go into an infinite loop.

#849 applecool closed 3 days ago
5
Feature Request - Beam Search Decoder

#846 r4ghu opened 1 week ago
0
[Feature Request] Finetuning Scripts for Whisper Models

#845 1rsh closed 1 week ago
1
01-ai/Yi-6B-Chat got IndexError: list assignment index out of range

#844 yong326 closed 4 days ago
2
iterate_batches in mlx_lm's Lora trainer is discarding the remainder dataset items (modulo batch size)

#843 chimezie opened 1 week ago
1
Error loading GGUF Mixtral 8x7B Q_8 model

#842 HaskDev0 closed 5 days ago
1
lora resume error

#841 l0d0v1c closed 1 week ago
2
added docstring explanation for bertenbeddings class in model.py in…

#840 saul1310 closed 1 week ago
1
Refactor and Improve Image-to-Text Generation Script

#839 sanowl opened 2 weeks ago
1
transformer_lm: add --dataset enwik8

#838 proger closed 4 days ago
0
Openlm

#837 awni closed 6 days ago
1
mlx_lm stops generating

#836 stefanvarunix closed 2 weeks ago
1
Fix mypy errors with models/{qwen2,qwen2_moe,startcoder2}.py

#835 wangkuiyi closed 2 weeks ago
0
Struggling to convert models to MLX

#834 Paramstr closed 2 weeks ago
2
make models/phi3.py and models/phi3small.py compatible with mypy

#833 wangkuiyi closed 2 weeks ago
0
Fusing adapters with llama3 cause bad performances

#832 Timelessprod opened 2 weeks ago
3
Add Support for Full Model Fine-Tuning

#831 Goekdeniz-Guelmez opened 2 weeks ago
1
Add mypy to .pre-commit-config.yml

#830 wangkuiyi closed 2 weeks ago
3
Proposal: Add mypy to .pre-commit-config.yml

#829 wangkuiyi opened 2 weeks ago
2
Correct the type annotation of cache in llama.py

#828 wangkuiyi closed 2 weeks ago
3
Correct type annotation of llama.ModelArgs.num_key_value_heads

#827 wangkuiyi closed 2 weeks ago
0
Add functions for input-masked loss calculation and padded batching

#825 chimezie opened 3 weeks ago
0
GPU featurization for Whisper example

#824 awni closed 3 weeks ago
0
Unable to allocate memory

#823 aidinrs opened 3 weeks ago
0
Fix Qwen2 moe

#822 Blaizzy closed 3 weeks ago
8
Enable distributed LoRA training

#821 angeloskath opened 3 weeks ago
0
LLMEvaluator : libc++abi: terminating due to uncaught exception of type std::invalid_argument: [matmul] Last dimension of first input with shape (1,916,2048) must match second to last dimension of second input with shape (256,32000)

#820 Paramstr closed 2 weeks ago
0
Error when running inference on newly converted OpenELM MLX model, ValueError(f"Received parameters not in model: {extras}.")

#819 Paramstr closed 3 weeks ago
1
Add eos token to lora fine-tunes

#818 awni closed 2 weeks ago
0
Fix NameError in lora.py when loading pretrained adapters

#817 nahakiole closed 3 weeks ago
1
[Feature] Export Lora Adapters as GGML

#816 rmarnold opened 3 weeks ago
3
[Model Request] Add support for IBM's Granite model

#815 sealad886 closed 3 weeks ago
2
[Feature] Export Lora Adapters as GGML

#848 rmarnold closed 4 days ago
1
[QUESTION] Is there a way to provide a Huggingface access token for downloading models that are private?

#814 Paramstr closed 3 weeks ago
1
Su-RoPE(Rotary Position Embedding) for Phi-3

#813 JosefAlbers closed 2 weeks ago
10
gpt-neox

#847 aPaleBlueDot opened 3 weeks ago
4
[Question]about creating the 'adapters.npz' file

#812 Daniel-Lee closed 3 weeks ago
3
A simple enhancement, in dataset creation time

#811 mustangs0786 closed 2 weeks ago
1
Tweaks to run dspy-produced calls to the server, with gemma template.

#810 namin closed 2 weeks ago
8
Why change the module decomposition of whisper

#809 m-a-sch closed 4 weeks ago
3