Upload LlamaForCausalLM
Browse files- README.md +0 -2
- config.json +1 -1
README.md
CHANGED
|
@@ -140,8 +140,6 @@ extra_gated_heading: Please be sure to provide your full legal name, date of bir
|
|
| 140 |
|
| 141 |
**Tri-21B**를 4bit으로 양자화한 모델
|
| 142 |
|
| 143 |
-
https://huggingface.co/trillionlabs/Tri-21B
|
| 144 |
-
|
| 145 |
We introduce **Tri-21B**, our flagship large language model that redefines the efficiency frontier in LLM training. By achieving state-of-the-art performance with only 2.3T training tokens, we demonstrate that exceptional capabilities don't require excessive computational resources.
|
| 146 |
|
| 147 |
<p align="center">
|
|
|
|
| 140 |
|
| 141 |
**Tri-21B**를 4bit으로 양자화한 모델
|
| 142 |
|
|
|
|
|
|
|
| 143 |
We introduce **Tri-21B**, our flagship large language model that redefines the efficiency frontier in LLM training. By achieving state-of-the-art performance with only 2.3T training tokens, we demonstrate that exceptional capabilities don't require excessive computational resources.
|
| 144 |
|
| 145 |
<p align="center">
|
config.json
CHANGED
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"quantization_config": {
|
| 24 |
"_load_in_4bit": true,
|
| 25 |
"_load_in_8bit": false,
|
| 26 |
-
"bnb_4bit_compute_dtype": "
|
| 27 |
"bnb_4bit_quant_storage": "uint8",
|
| 28 |
"bnb_4bit_quant_type": "nf4",
|
| 29 |
"bnb_4bit_use_double_quant": false,
|
|
|
|
| 23 |
"quantization_config": {
|
| 24 |
"_load_in_4bit": true,
|
| 25 |
"_load_in_8bit": false,
|
| 26 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 27 |
"bnb_4bit_quant_storage": "uint8",
|
| 28 |
"bnb_4bit_quant_type": "nf4",
|
| 29 |
"bnb_4bit_use_double_quant": false,
|