2.59 GB

Ctrl+K

2 contributors

flm-add.py: fix -A3B size suffix (35b-a3b) and add family aliases (granite/llama, darwin/qwen3.6-moe, crow/qwythos/qwopus/huihui/qwen3.5, gemma-4/gemma4e)

4c9021f verified 1 day ago

.gitattributes

1.57 kB
Duplicate from FastFlowLM/Qwen2.5-3B-Instruct-NPU2 2 days ago
README.md

3.18 kB
Q4NX/FastFlowLM card: flm-add.py install + run/serve flow, kernels source, model info 1 day ago
chat_template.jinja

2.51 kB
Upload chat_template.jinja with huggingface_hub 2 days ago
config.json

745 Bytes
Upload config.json with huggingface_hub 2 days ago
flm-add.py

24.4 kB
flm-add.py: fix -A3B size suffix (35b-a3b) and add family aliases (granite/llama, darwin/qwen3.6-moe, crow/qwythos/qwopus/huihui/qwen3.5, gemma-4/gemma4e) 1 day ago
model.q4nx

2.59 GB
xet

Upload model.q4nx with huggingface_hub 2 days ago
tokenizer.json

7.03 MB
Duplicate from FastFlowLM/Qwen2.5-3B-Instruct-NPU2 2 days ago
tokenizer_config.json

7.41 kB
Upload tokenizer_config.json with huggingface_hub 2 days ago