Comments (1)
@helldog-star
For GLA
{
"attn_mode": "chunk",
"bos_token_id": 1,
"eos_token_id": 2,
"expand_k": 0.5,
"expand_v": 1,
"fuse_cross_entropy": true,
"fuse_norm": true,
"hidden_act": "swish",
"hidden_ratio": 4,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": null,
"max_position_embeddings": 2048,
"model_type": "gla",
"num_heads": 4,
"num_hidden_layers": 24,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": true,
"transformers_version": "4.40.0",
"use_cache": true,
"use_gk": true,
"use_gv": false,
"vocab_size": 32000
}
and for RetNet
{
"attn_mode": "chunk",
"bos_token_id": 1,
"eos_token_id": 2,
"expand_k": 1,
"expand_v": 2,
"fuse_cross_entropy": true,
"fuse_norm": true,
"hidden_act": "swish",
"hidden_ratio": 2,
"hidden_size": 1024,
"max_position_embeddings": 2048,
"model_type": "retnet",
"num_heads": 4,
"num_hidden_layers": 24,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": true,
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 32000
}
from flash-linear-attention.
Related Issues (19)
- Mistakes in the GLA paper HOT 4
- RWKV6 backward gives nan gradients HOT 1
- Error loading pretrained checkpoints through `transformers` library HOT 1
- Using operators without having `transformers` installed HOT 3
- Finetune RWKV6 with fla implementations (使用fla中的rwkv6微调) HOT 8
- "Fla" currently downloaded via pip does not support rwkv6. Please update. HOT 2
- RWKV6 backward issue HOT 15
- 更新后的rwkv6,loss会nan HOT 16
- inconsistent results when "masking" gating term between "fused_recurrent" and "fused_chunk" (fused_chunk presumably wrong) HOT 1
- Does the wkv6 operator now support parallel inference? HOT 2
- AssertionError('All values in both first input shape ([constexpr[16], constexpr[8]]) and second input shape ([constexpr[8], constexpr[16]]) must be >= 16!') HOT 17
- missing hidden_size in linear attention HOT 1
- IS there any speed(train and inference) and memory benchmarking comparison between GLA and Mamba? HOT 1
- RuntimeError: Triton Error [CUDA]: device kernel image is invalid HOT 6
- Could you share the ckpt of 340M and 1.3B model? HOT 3
- 'RebasedFeatureMap' is missing? HOT 4
- illegal memory access error HOT 2
- Triton Error in flash-linear-attention/fla/modules/rmsnorm.py HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from flash-linear-attention.