Instructions to use corechan/MiniMax-H3_NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use corechan/MiniMax-H3_NF4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("corechan/MiniMax-H3_NF4", dtype=torch.bfloat16, device_map="cuda") prompt = "Hi, what can you help me with?" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
quantized text_encoder (nf4) from memory
Browse files
quantized/text_encoder-nf4/.complete
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"component": "text_encoder", "quant": "nf4", "ts":
|
|
|
|
| 1 |
+
{"component": "text_encoder", "quant": "nf4", "ts": 1787925084.5835261}
|
quantized/text_encoder-nf4/config.json
CHANGED
|
@@ -57,7 +57,7 @@
|
|
| 57 |
"vocab_size": 151936
|
| 58 |
},
|
| 59 |
"tie_word_embeddings": false,
|
| 60 |
-
"transformers_version": "5.
|
| 61 |
"video_token_id": 151656,
|
| 62 |
"vision_config": {
|
| 63 |
"deepstack_visual_indexes": [
|
|
|
|
| 57 |
"vocab_size": 151936
|
| 58 |
},
|
| 59 |
"tie_word_embeddings": false,
|
| 60 |
+
"transformers_version": "5.15.1",
|
| 61 |
"video_token_id": 151656,
|
| 62 |
"vision_config": {
|
| 63 |
"deepstack_visual_indexes": [
|
quantized/text_encoder-nf4/generation_config.json
CHANGED
|
@@ -2,6 +2,6 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151643,
|
| 4 |
"eos_token_id": 151645,
|
| 5 |
-
"transformers_version": "5.
|
| 6 |
"use_cache": true
|
| 7 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151643,
|
| 4 |
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "5.15.1",
|
| 6 |
"use_cache": true
|
| 7 |
}
|