Downloads · 30 days
6
19% of all-time downloads
Magistral-Small-2506-W8A8
noneUsername/Magistral-Small-2506-W8A8
Magistral-Small-2506-W8A8 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/Magistral-Small-2506,addbostoken=true,maxmodellen=3096,dtype=bfloat16,trustremotecode=true), genkwargs: (None), limit: 250.0, numfewshot: 5, batchsize: auto
All-time downloads
31
Public
Parameters
23.6B
24.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors24.9 GB · 100%
Parameter types
How the weights are stored.
I822.2B · 94%
Base models
Model card
From the Hugging Face model README
vllm (pretrained=/root/autodl-tmp/Magistral-Small-2506,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=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 | ↑ | 0.924 | ± | 0.0168 |
| strict-match | 5 | exact_match | ↑ | 0.920 | ± | 0.0172 |
vllm (pretrained=/root/autodl-tmp/Magistral-Small-2506,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.916 | ± | 0.0124 |
| strict-match | 5 | exact_match | ↑ | 0.912 | ± | 0.0127 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.7766 | ± | 0.0134 | |
| - humanities | 2 | none | acc | ↑ | 0.8154 | ± | 0.0259 | |
| - other | 2 | none | acc | ↑ | 0.8308 | ± | 0.0266 | |
| - social sciences | 2 | none | acc | ↑ | 0.8056 | ± | 0.0282 | |
| - stem | 2 | none | acc | ↑ | 0.6947 | ± | 0.0256 |
vllm (pretrained=/root/autodl-tmp/root90-256-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=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 | ↑ | 0.908 | ± | 0.0183 |
| strict-match | 5 | exact_match | ↑ | 0.904 | ± | 0.0187 |
llm (pretrained=/root/autodl-tmp/root90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=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 | ↑ | 0.924 | ± | 0.0168 |
| strict-match | 5 | exact_match | ↑ | 0.920 | ± | 0.0172 |
vllm (pretrained=/root/autodl-tmp/root90-128-4096-9.9999,add_bos_token=true,max_model_len=3096,dtype=bfloat16,trust_remote_code=true), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.912 | ± | 0.0127 |
| strict-match | 5 | exact_match | ↑ | 0.906 | ± | 0.0131 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.7754 | ± | 0.0135 | |
| - humanities | 2 | none | acc | ↑ | 0.7949 | ± | 0.0268 | |
| - other | 2 | none | acc | ↑ | 0.8103 | ± | 0.0278 | |
| - social sciences | 2 | none | acc | ↑ | 0.8278 | ± | 0.0273 | |
| - stem | 2 | none | acc | ↑ | 0.7053 | ± | 0.0254 |
- Type
- mistral
- Created
- Jun 11, 2025
- Updated
- Jun 11, 2025