Question Answering
Transformers
Safetensors
English
mistral
text-generation
text-generation-inference
8-bit precision
gptq
Instructions to use Tijmen2/cosmosage_v1_gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tijmen2/cosmosage_v1_gptq with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Tijmen2/cosmosage_v1_gptq")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Tijmen2/cosmosage_v1_gptq") model = AutoModelForCausalLM.from_pretrained("Tijmen2/cosmosage_v1_gptq") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +12 -1
config.json
CHANGED
|
@@ -22,5 +22,16 @@
|
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.37.1",
|
| 24 |
"use_cache": false,
|
| 25 |
-
"vocab_size": 32000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
|
|
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.37.1",
|
| 24 |
"use_cache": false,
|
| 25 |
+
"vocab_size": 32000,
|
| 26 |
+
"quantization_config":{
|
| 27 |
+
"bits": 8,
|
| 28 |
+
"group_size": 128,
|
| 29 |
+
"damp_percent": 0.01,
|
| 30 |
+
"desc_act": false,
|
| 31 |
+
"static_groups": false,
|
| 32 |
+
"sym": true,
|
| 33 |
+
"true_sequential": true,
|
| 34 |
+
"model_name_or_path": null,
|
| 35 |
+
"model_file_base_name": null
|
| 36 |
+
}
|
| 37 |
}
|