Downloads · 30 days
8
23% of all-time downloads
OpenMOSE/RWKV-Qwen3-30B-A3B-Instruct-cxa07c
RWKV-Qwen3-30B-A3B-Instruct-cxa07c is a machine learning model from OpenMOSE. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Downloads · 30 days
8
23% of all-time downloads
All-time downloads
35
Public
Parameters
30.7B
61.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors61.5 GB · 100%
From the Hugging Face model README
this is full RWKV
hf (pretrained=/workspace/output/qwen3-30b/hf_temp_cxa07c,trust_remote_code=True), gen_kwargs: (max_gen_toks=10), limit: None, num_fewshot: None, batch_size: 4
| Tasks |Version|Filter|n-shot|Metric| |Value| |Stderr|
|-------------|------:|------|-----:|-----:|---|----:|---|------|
|niah_single_1| 1|none | 0| 16384|↑ |0.378|± | N/A|
| | |none | 0| 2048| |0.996|± |0.0028|
| | |none | 0| 4096|↑ |0.942|± | N/A|
| | |none | 0| 8192|↑ |0.840|± | N/A|
hf (pretrained=/workspace/output/qwen3-30b/hf_temp_cxa07c,trust_remote_code=True), gen_kwargs: (max_gen_toks=64), limit: None, num_fewshot: None, batch_size: 4
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|--------|------:|------|-----:|-----:|---|-----:|---|------|
|ruler_vt| 1|none | 0| 4096|↑ |0.4144|± | N/A|
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu | 2|none | |acc |↑ |0.7477|± |0.0034|
| - humanities | 2|none | |acc |↑ |0.6227|± |0.0063|
| - other | 2|none | |acc |↑ |0.8072|± |0.0068|
| - social sciences| 2|none | |acc |↑ |0.8560|± |0.0062|
| - stem | 2|none | |acc |↑ |0.7697|± |0.0073|