Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,7 @@ datasets:
|
|
| 3 |
- Rombo-Org/Optimized_Reasoning
|
| 4 |
base_model:
|
| 5 |
- CohereLabs/command-a-reasoning-08-2025
|
|
|
|
| 6 |
---
|
| 7 |
# command-a-reasoning-08-2025-nvfp4
|
| 8 |
|
|
@@ -18,6 +19,6 @@ Check the original model card for information about this model.
|
|
| 18 |
```sh
|
| 19 |
sudo docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:nightly --model Firworks/command-a-reasoning-08-2025-nvfp4 --dtype auto --max-model-len 32768
|
| 20 |
```
|
| 21 |
-
This was tested on
|
| 22 |
|
| 23 |
-
If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to allow more people to try them out.
|
|
|
|
| 3 |
- Rombo-Org/Optimized_Reasoning
|
| 4 |
base_model:
|
| 5 |
- CohereLabs/command-a-reasoning-08-2025
|
| 6 |
+
license: cc-by-nc-4.0
|
| 7 |
---
|
| 8 |
# command-a-reasoning-08-2025-nvfp4
|
| 9 |
|
|
|
|
| 19 |
```sh
|
| 20 |
sudo docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:nightly --model Firworks/command-a-reasoning-08-2025-nvfp4 --dtype auto --max-model-len 32768
|
| 21 |
```
|
| 22 |
+
This was tested on an RTX Pro 6000 Blackwell cloud instance.
|
| 23 |
|
| 24 |
+
If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to allow more people to try them out.
|