Steve Chen

stev236's activity

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

New activity in LiquidAI/LFM2-8B-A1B 2 days ago

No file named configuration_lfm2_moe.py

3

#3 opened 12 days ago by

Mohaddz

New activity in ibm-granite/granite-4.0-h-small 12 days ago

Quantization results in model not supporting Tensor Parallel mode.

#3 opened 17 days ago by

stev236

New activity in Qwen/Qwen3-Omni-30B-A3B-Instruct 17 days ago

Quantization issues

4

#17 opened 23 days ago by

stev236

New activity in Qwen/Qwen3-Coder-30B-A3B-Instruct 2 months ago

Treating _ as * (tokenizer error?)

5

#10 opened 3 months ago by

EmilPi

New activity in openai/gpt-oss-20b 2 months ago

This model is unbelievably ignorant.

➕ 👍 40

15

#14 opened 3 months ago by

phil111

how to make determinstic output?

4

#23 opened 3 months ago by

junma

New activity in tencent/Hunyuan-7B-Instruct 2 months ago

not able to use this model (tencent/Hunyuan-7B-Instruct) via vllm

➕ 8

2

#5 opened 3 months ago by

aditya-shinde

New activity in tencent/Hunyuan-7B-Instruct 3 months ago

Readme says 256k context, but config.json has "max_position_embeddings": 32768

➕ 1

#4 opened 3 months ago by

stev236

Local Installation Video and Testing - Step by Step

😎 1

1

#2 opened 3 months ago by

fahdmirzac

New activity in Qwen/Qwen3-14B 3 months ago

Long context: YaRN max_position_embeddings 32K or 40k?

➕ 1

2

#10 opened 6 months ago by

stev236

New activity in Qwen/Qwen3-8B 3 months ago

New 8B model much slower than old 7B model when running on vLLM.

1

#6 opened 5 months ago by

stev236

New activity in Qwen/Qwen3-4B 3 months ago

Why are the new 4B and 8B models slower than the previous 7B-1M model??

3

#6 opened 6 months ago by

stev236

New activity in Qwen/Qwen2.5-14B-Instruct-1M 3 months ago

Hardware requirements?

🤯 1

2

#7 opened 9 months ago by

ccocks-deca

Does vllm 0.7.3 support this model？

1

#10 opened 8 months ago by

traphix

Model no longer working with vLLM > v.0.8.5

1

#13 opened 3 months ago by

stev236

New activity in Qwen/Qwen2.5-7B-Instruct-1M 3 months ago

Did anybody notice that this model no longer works with vLLM > v.0.8.5?

1

#7 opened 3 months ago by

stev236

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 6 months ago

vLLM example for 'Offline' should include an input image.

❤️ 1

2

#47 opened 7 months ago by

stev236

vLLM example for 'Offline' should include an input image.

❤️ 1

2

#47 opened 7 months ago by

stev236