Downloads · 30 days
9
28% of all-time downloads
Mistral-Small-22B-ArliAI-RPMax-v1.1-W8A8-Dynamic-Per-Token
noneUsername/Mistral-Small-22B-ArliAI-RPMax-v1.1-W8A8-Dynamic-Per-Token
Mistral-Small-22B-ArliAI-RPMax-v1.1-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/Mistral-Small-22B-ArliAI-RPMax-v1.1,addbostoken=true,tensorparallelsize=2,maxmodellen=2048,enforceeager=true,gpumemoryutilization=0.99), genkwargs: (None), limit: 250.0, numfewshot: 5…
All-time downloads
32
Public
Parameters
22.3B
22.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.7 GB · 100%
Parameter types
How the weights are stored.
I821.8B · 98%
Base models
Model card
From the Hugging Face model README
vllm (pretrained=/root/autodl-tmp/Mistral-Small-22B-ArliAI-RPMax-v1.1,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,enforce_eager=true,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 | ↑ | 0.764 | ± | 0.0269 |
| strict-match | 5 | exact_match | ↑ | 0.752 | ± | 0.0274 |
vllm (pretrained=/root/autodl-tmp/output,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,enforce_eager=true), 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 | ↑ | 0.756 | ± | 0.0272 |
| strict-match | 5 | exact_match | ↑ | 0.752 | ± | 0.0274 |
- Type
- mistral
- Created
- Oct 7, 2024
- Updated
- Oct 19, 2024