Add files using upload-large-folder tool
Browse files- README.md +1 -1
- config.json +1 -1
README.md
CHANGED
|
@@ -45,7 +45,7 @@ tags:
|
|
| 45 |
|
| 46 |
The Model [mlx-community/c4ai-command-a-03-2025-8bit](https://huggingface.co/mlx-community/c4ai-command-a-03-2025-8bit) was
|
| 47 |
converted to MLX format from [CohereForAI/c4ai-command-a-03-2025](https://huggingface.co/CohereForAI/c4ai-command-a-03-2025)
|
| 48 |
-
using mlx-lm version **0.
|
| 49 |
|
| 50 |
## Use with mlx
|
| 51 |
|
|
|
|
| 45 |
|
| 46 |
The Model [mlx-community/c4ai-command-a-03-2025-8bit](https://huggingface.co/mlx-community/c4ai-command-a-03-2025-8bit) was
|
| 47 |
converted to MLX format from [CohereForAI/c4ai-command-a-03-2025](https://huggingface.co/CohereForAI/c4ai-command-a-03-2025)
|
| 48 |
+
using mlx-lm version **0.22.0**.
|
| 49 |
|
| 50 |
## Use with mlx
|
| 51 |
|
config.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"intermediate_size": 36864,
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"logit_scale": 0.25,
|
| 17 |
-
"max_position_embeddings":
|
| 18 |
"model_type": "cohere2",
|
| 19 |
"num_attention_heads": 96,
|
| 20 |
"num_hidden_layers": 64,
|
|
|
|
| 14 |
"intermediate_size": 36864,
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"logit_scale": 0.25,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
"model_type": "cohere2",
|
| 19 |
"num_attention_heads": 96,
|
| 20 |
"num_hidden_layers": 64,
|