Downloads · 30 days
9
7% of all-time downloads
Qwen2.5-Lumen-14B-W8A8-Dynamic-Per-Token
noneUsername/Qwen2.5-Lumen-14B-W8A8-Dynamic-Per-Token
Qwen2.5-Lumen-14B-W8A8-Dynamic-Per-Token is a machine learning model from noneUsername. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
vllm (pretrained=/root/autodl-tmp/Qwen2.5-Lumen-14B,addbostoken=true,tensorparallelsize=2,maxmodellen=2048,gpumemoryutilization=0.99), genkwargs: (None), limit: 250.0, numfewshot: 5, batchsize: auto
All-time downloads
125
Public
Parameters
14.8B
16.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.3 GB · 100%
Parameter types
How the weights are stored.
I813.2B · 89%
Base models
Model card
From the Hugging Face model README
vllm (pretrained=/root/autodl-tmp/Qwen2.5-Lumen-14B,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.99), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.544 | ± | 0.0316 |
| strict-match | 5 | exact_match | ↑ | 0.836 | ± | 0.0235 |
vllm (pretrained=/root/autodl-tmp/output,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.99), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.532 | ± | 0.0316 |
| strict-match | 5 | exact_match | ↑ | 0.824 | ± | 0.0241 |
- Type
- qwen2
- Created
- Nov 8, 2024
- Updated
- Nov 12, 2024