Text Generation
Transformers
Safetensors
English
Chinese
Russian
yue2
music-generation
orbitquant
quantization
4-bit precision
custom-code
8-bit precision
Instructions to use WaveCut/YuE2-3B-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WaveCut/YuE2-3B-OrbitQuant-W4A4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WaveCut/YuE2-3B-OrbitQuant-W4A4")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("WaveCut/YuE2-3B-OrbitQuant-W4A4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WaveCut/YuE2-3B-OrbitQuant-W4A4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WaveCut/YuE2-3B-OrbitQuant-W4A4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WaveCut/YuE2-3B-OrbitQuant-W4A4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/WaveCut/YuE2-3B-OrbitQuant-W4A4
- SGLang
How to use WaveCut/YuE2-3B-OrbitQuant-W4A4 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "WaveCut/YuE2-3B-OrbitQuant-W4A4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WaveCut/YuE2-3B-OrbitQuant-W4A4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "WaveCut/YuE2-3B-OrbitQuant-W4A4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WaveCut/YuE2-3B-OrbitQuant-W4A4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use WaveCut/YuE2-3B-OrbitQuant-W4A4 with Docker Model Runner:
docker model run hf.co/WaveCut/YuE2-3B-OrbitQuant-W4A4
Keep only baseline and main fast audio demos
Browse files- .gitattributes +1 -0
- README.md +1 -1
- SHA256SUMS +2 -14
- examples/{runtime-v10/int8-ordered-cfg1.wav → fast-int8.wav} +0 -0
- examples/runtime-v10/int8-ordered-cfg1.5.wav +0 -3
- examples/runtime-v10/int8-subwarp-cfg1.5.wav +0 -3
- examples/runtime-v10/int8-subwarp-cfg1.wav +0 -3
- examples/runtime-v3/fast-rms.wav +0 -3
- examples/runtime-v4/fast-rms.wav +0 -3
- examples/runtime-v5/fast-rms.wav +0 -3
- examples/runtime-v6/fast-rms.wav +0 -3
- examples/runtime-v7/fast-rms-cfg1.5.wav +0 -3
- examples/runtime-v8/int8-kv-cfg1.5.wav +0 -3
- examples/runtime-v8/int8-kv-cfg1.wav +0 -3
- examples/runtime-v9/int8-kv-cfg1.5.wav +0 -3
- examples/runtime-v9/int8-kv-cfg1.wav +0 -3
.gitattributes
CHANGED
|
@@ -64,3 +64,4 @@ examples/runtime-v10/int8-subwarp-cfg1.5.wav filter=lfs diff=lfs merge=lfs -text
|
|
| 64 |
examples/runtime-v10/int8-subwarp-cfg1.wav filter=lfs diff=lfs merge=lfs -text
|
| 65 |
src/runtime/kernels/int8-ordered/torch210-cxx11-cu128-x86_64-linux/_int8_ordered_attention_cuda_29ba9ae.abi3.so filter=lfs diff=lfs merge=lfs -text
|
| 66 |
src/runtime/kernels/int8-subwarp/torch210-cxx11-cu128-x86_64-linux/_int8_subwarp_attention_cuda_92f98d4.abi3.so filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 64 |
examples/runtime-v10/int8-subwarp-cfg1.wav filter=lfs diff=lfs merge=lfs -text
|
| 65 |
src/runtime/kernels/int8-ordered/torch210-cxx11-cu128-x86_64-linux/_int8_ordered_attention_cuda_29ba9ae.abi3.so filter=lfs diff=lfs merge=lfs -text
|
| 66 |
src/runtime/kernels/int8-subwarp/torch210-cxx11-cu128-x86_64-linux/_int8_subwarp_attention_cuda_92f98d4.abi3.so filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
examples/fast-int8.wav filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -66,7 +66,7 @@ Rental rates: $0.72/h for PRO 4500 and $0.28/h for 4000 Ada, observed September
|
|
| 66 |
|
| 67 |
## Audio and limitations
|
| 68 |
|
| 69 |
-
|
| 70 |
|
| 71 |
Code and kernels are under `src/`; metrics under `evaluation/`; prompts and audio under `examples/`. [SHA256SUMS](SHA256SUMS) and [runtime-lock.json](src/runtime-lock.json) pin the shipped artifacts.
|
| 72 |
|
|
|
|
| 66 |
|
| 67 |
## Audio and limitations
|
| 68 |
|
| 69 |
+
WAV demos: [original BF16](examples/original-ru.wav), [W4A4 reference](examples/orbitquant-ru.wav), [fast INT8 KV](examples/fast-int8.wav). Experimental RMS fusion, INT8 KV and attention reductions can change the arrangement at the same seed. Spectral similarity is a diagnostic, not proof of perceptual equivalence. Russian was tested on this prompt; upstream advertises Chinese and English.
|
| 70 |
|
| 71 |
Code and kernels are under `src/`; metrics under `evaluation/`; prompts and audio under `examples/`. [SHA256SUMS](SHA256SUMS) and [runtime-lock.json](src/runtime-lock.json) pin the shipped artifacts.
|
| 72 |
|
SHA256SUMS
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
060985741d20e70613b4c189c7de106cabd3fb2109fbbfb6d705c9d619417dd0 LICENSE
|
| 2 |
-
|
| 3 |
14d3fd9f6fee86b4260b69b0979735b99ffec8c6b4db254567047a4215cd9af3 THIRD_PARTY_NOTICES.md
|
| 4 |
e479ab4f807b93d4c945ae9a14c5269dafb34751ee059d29f9883a5e812f2e56 config.json
|
| 5 |
5e375ad03c84d8118f3b37e56a3d01cf137b5aa1526b5725d91b17857839616d evaluation/ar-fused-fixed.json
|
|
@@ -631,22 +631,10 @@ a8a166b2e235fbc927eb3dc017e47e04255a6015461376743c4843b79a629445 evaluation/run
|
|
| 631 |
77c897a1fdf3e8a94bbfb828d5e5a766d0f036521da10a0c06fbe45021bedc89 evaluation/runtime-v9/v9-full/output.log
|
| 632 |
acac9c9098eaffec853d3fe5b10cb23acfab49d239e5dc153042c741c04d8682 evaluation/runtime-v9/v9-full/status.json
|
| 633 |
00da89c0d8a7242efb498fc30f221fab25b0becc127a61079a528d333be229df evaluation/vae-chunk-benchmark.json
|
|
|
|
| 634 |
6daa417ffd2972c8a7f681083ca59f131a03b9f5caf62871a9f37ec30905179a examples/orbitquant-ru.wav
|
| 635 |
4879336415f868fe92e0d0d21733dea194c09f8deb10484c27add434950b4bb6 examples/original-ru.wav
|
| 636 |
a67f3becd1edcc3c42c2602735b47d455bf76cf1258862a3fe5978cf87fb16b0 examples/prompts/default-ru.json
|
| 637 |
-
1d4e9cf0eb5a6b71fd27faf82da465c274ff162573f7ba24e895e1b4aa79293c examples/runtime-v10/int8-ordered-cfg1.5.wav
|
| 638 |
-
7e66bfe39c6a34e6aeae47cd7b2e1d0a58995fecbe1302579bda53cc8a06ffcf examples/runtime-v10/int8-ordered-cfg1.wav
|
| 639 |
-
f4a59733814697406704a6dad96418abee0ac5d386a4fe1352b1b72ae0d06c9a examples/runtime-v10/int8-subwarp-cfg1.5.wav
|
| 640 |
-
03c1d1c79b6611c34fafbc2ac0d7f460a2b9bfbc847abf96adf5c0639a37ec83 examples/runtime-v10/int8-subwarp-cfg1.wav
|
| 641 |
-
30a70e2224b008e08f10ba0e0f9b8243b06b32a4fcbd7381e980d68cd5a7974e examples/runtime-v3/fast-rms.wav
|
| 642 |
-
d314b4b9876095782a7b0aabf7b0de6c96b4d2f203809e14c2318c166c569dec examples/runtime-v4/fast-rms.wav
|
| 643 |
-
e0693fca03f50e48d597a3e22607df6b383a28de44be5d59e243807e97b98e44 examples/runtime-v5/fast-rms.wav
|
| 644 |
-
78b6257e68ef5f003ebce4cd582b610d94cbbb1c4322384bdb2b60a7e47157d0 examples/runtime-v6/fast-rms.wav
|
| 645 |
-
1cfad8b2c95630da7630dfb87723bea1175f4b6fbcf2916e993bb606bce4aabe examples/runtime-v7/fast-rms-cfg1.5.wav
|
| 646 |
-
8c88e3aad65b435efb880c24962c8d455b76b2c486d45cff97dea1e2c3444844 examples/runtime-v8/int8-kv-cfg1.5.wav
|
| 647 |
-
7ec97d940b7b5d3065a0fc09ce5ae73d37e09b12749e444afd5e5c142b9fd7bb examples/runtime-v8/int8-kv-cfg1.wav
|
| 648 |
-
212b2abc44b8ce5f51a1cbb2b75f56fea047f7706675044ee2b2ee0ae2f584df examples/runtime-v9/int8-kv-cfg1.5.wav
|
| 649 |
-
2831fb6e362b393ae13a8b2aa1346da39835f8c68a45c0afc2b3ef665870517e examples/runtime-v9/int8-kv-cfg1.wav
|
| 650 |
ccc842772f029049fadf9b288393bcdd9f79271b361c0f1875ec1218e4ba5170 generation_config.json
|
| 651 |
da9858d516047d82096d01c112a61bd67f26d289039464d668a1d45f91738ecc licenses/SnakeBeta-NVIDIA-MIT.txt
|
| 652 |
a1fac33b7bcd791b74fb33aeb439f825e7277e239fc119fb7d2ab6f084a0c101 licenses/stable-audio-tools-MIT.txt
|
|
|
|
| 1 |
060985741d20e70613b4c189c7de106cabd3fb2109fbbfb6d705c9d619417dd0 LICENSE
|
| 2 |
+
d8b6905c3c2fb2e74c364e1844577fba3af08370d7d01663fb950f75e06e0dae README.md
|
| 3 |
14d3fd9f6fee86b4260b69b0979735b99ffec8c6b4db254567047a4215cd9af3 THIRD_PARTY_NOTICES.md
|
| 4 |
e479ab4f807b93d4c945ae9a14c5269dafb34751ee059d29f9883a5e812f2e56 config.json
|
| 5 |
5e375ad03c84d8118f3b37e56a3d01cf137b5aa1526b5725d91b17857839616d evaluation/ar-fused-fixed.json
|
|
|
|
| 631 |
77c897a1fdf3e8a94bbfb828d5e5a766d0f036521da10a0c06fbe45021bedc89 evaluation/runtime-v9/v9-full/output.log
|
| 632 |
acac9c9098eaffec853d3fe5b10cb23acfab49d239e5dc153042c741c04d8682 evaluation/runtime-v9/v9-full/status.json
|
| 633 |
00da89c0d8a7242efb498fc30f221fab25b0becc127a61079a528d333be229df evaluation/vae-chunk-benchmark.json
|
| 634 |
+
7e66bfe39c6a34e6aeae47cd7b2e1d0a58995fecbe1302579bda53cc8a06ffcf examples/fast-int8.wav
|
| 635 |
6daa417ffd2972c8a7f681083ca59f131a03b9f5caf62871a9f37ec30905179a examples/orbitquant-ru.wav
|
| 636 |
4879336415f868fe92e0d0d21733dea194c09f8deb10484c27add434950b4bb6 examples/original-ru.wav
|
| 637 |
a67f3becd1edcc3c42c2602735b47d455bf76cf1258862a3fe5978cf87fb16b0 examples/prompts/default-ru.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 638 |
ccc842772f029049fadf9b288393bcdd9f79271b361c0f1875ec1218e4ba5170 generation_config.json
|
| 639 |
da9858d516047d82096d01c112a61bd67f26d289039464d668a1d45f91738ecc licenses/SnakeBeta-NVIDIA-MIT.txt
|
| 640 |
a1fac33b7bcd791b74fb33aeb439f825e7277e239fc119fb7d2ab6f084a0c101 licenses/stable-audio-tools-MIT.txt
|
examples/{runtime-v10/int8-ordered-cfg1.wav → fast-int8.wav}
RENAMED
|
File without changes
|
examples/runtime-v10/int8-ordered-cfg1.5.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1d4e9cf0eb5a6b71fd27faf82da465c274ff162573f7ba24e895e1b4aa79293c
|
| 3 |
-
size 63328856
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v10/int8-subwarp-cfg1.5.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f4a59733814697406704a6dad96418abee0ac5d386a4fe1352b1b72ae0d06c9a
|
| 3 |
-
size 69503576
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v10/int8-subwarp-cfg1.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:03c1d1c79b6611c34fafbc2ac0d7f460a2b9bfbc847abf96adf5c0639a37ec83
|
| 3 |
-
size 69795416
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v3/fast-rms.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:30a70e2224b008e08f10ba0e0f9b8243b06b32a4fcbd7381e980d68cd5a7974e
|
| 3 |
-
size 70455896
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v4/fast-rms.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d314b4b9876095782a7b0aabf7b0de6c96b4d2f203809e14c2318c166c569dec
|
| 3 |
-
size 70455896
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v5/fast-rms.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e0693fca03f50e48d597a3e22607df6b383a28de44be5d59e243807e97b98e44
|
| 3 |
-
size 70455896
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v6/fast-rms.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:78b6257e68ef5f003ebce4cd582b610d94cbbb1c4322384bdb2b60a7e47157d0
|
| 3 |
-
size 70455896
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v7/fast-rms-cfg1.5.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1cfad8b2c95630da7630dfb87723bea1175f4b6fbcf2916e993bb606bce4aabe
|
| 3 |
-
size 70640216
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v8/int8-kv-cfg1.5.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8c88e3aad65b435efb880c24962c8d455b76b2c486d45cff97dea1e2c3444844
|
| 3 |
-
size 63328856
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v8/int8-kv-cfg1.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7ec97d940b7b5d3065a0fc09ce5ae73d37e09b12749e444afd5e5c142b9fd7bb
|
| 3 |
-
size 63912536
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v9/int8-kv-cfg1.5.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:212b2abc44b8ce5f51a1cbb2b75f56fea047f7706675044ee2b2ee0ae2f584df
|
| 3 |
-
size 63328856
|
|
|
|
|
|
|
|
|
|
|
|
examples/runtime-v9/int8-kv-cfg1.wav
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2831fb6e362b393ae13a8b2aa1346da39835f8c68a45c0afc2b3ef665870517e
|
| 3 |
-
size 63912536
|
|
|
|
|
|
|
|
|
|
|
|