Christian Otto Stelter PRO

stelterlab's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in audreyt/Kolibri-1-NVFP4-W4A16 7 days ago

Works on RTX PRO 6000

#1 opened 7 days ago by

stelterlab

New activity in Aleph-Alpha/Kolibri-1 7 days ago

DGX Spark recipe

👍 2

#5 opened 7 days ago by

stelterlab

tool-eval-bench results

👍 6

1

#4 opened 7 days ago by

stelterlab

transformers support for Kolibri1ForCausalLM

2

#2 opened 8 days ago by

stelterlab

llama.cpp support?

➕ 6

4

#3 opened 8 days ago by

jacek2024

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 7 months ago

Add documentation on how to use with vLLM to README.md

🤝👍 6

1

#7 opened 7 months ago by

stelterlab

New activity in stelterlab/Qwen3-30B-A3B-Instruct-2507-AWQ 7 months ago

Qwen3.5-35B-A3B AWQ quant planned?

2

#1 opened 7 months ago by

amidwestnoob

New activity in RedHatAI/Qwen3.5-397B-A17B-FP8-dynamic 8 months ago

Which transformer version did you use?

#3 opened 8 months ago by

stelterlab

New activity in stelterlab/NVIDIA-Nemotron-3-Nano-30B-A3B-AWQ 8 months ago

tokenizer_config.json missing chat_template field (tool calling broken without workaround)

1

#1 opened 8 months ago by

seanthomaswilliams

Updated tokenizer_config.json now w/ chat_template included

#2 opened 8 months ago by

stelterlab

New activity in mistralai/Ministral-3-14B-Instruct-2512 10 months ago

NVFP4 / AWQ Quants or llm-compressor recipe

🤗 2

1

#1 opened 10 months ago by

stelterlab

New activity in cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit 11 months ago

vLLM v0.11.1 seems to work, but v0.11.2 fails

👍❤️ 2

9

#3 opened 11 months ago by

stelterlab

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit about 1 year ago

Error when running in VLLM

👍 2

21

#1 opened about 1 year ago by

d8rt8v

New activity in stelterlab/Qwen3-Coder-30B-A3B-Instruct-AWQ about 1 year ago

Unable to run the model in VLLM: KeyError: 'layers.14.mlp.gate.qweight'

3

#1 opened about 1 year ago by

fredericodeveloper

New activity in stelterlab/DeepSeek-R1-0528-Qwen3-8B-AWQ about 1 year ago

Rope Scaling pre-applied?

6

#1 opened about 1 year ago by

the1dv

New activity in mistralai/Mistral-Small-3.2-24B-Instruct-2506 about 1 year ago

AWQ version

👍 14

13

#8 opened over 1 year ago by

celsowm

New activity in OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym over 1 year ago

How did you use auto-round to quantize?

3

#4 opened over 1 year ago by

stelterlab

New activity in stelterlab/Mistral-Small-24B-Instruct-2501-AWQ over 1 year ago

please update to Mistral-Small-3.2-24B-Instruct-2506

1

#5 opened over 1 year ago by

celsowm

Tool Calling issue with stelterlab/Mistral-Small-24B-Instruct-2501-AWQ

1

#4 opened over 1 year ago by

sbhatt765

New activity in stelterlab/Qwen3-32B-AWQ over 1 year ago

Do you any plan to quantize the Qwen3-30B-A3B-AWQ model?

1

#2 opened over 1 year ago by

Jeanxx