Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: text-generation
|
|
17 |
DPO fine-tuned of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) (3.82B params)
|
18 |
using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/jpacifico/french-orca-dpo-pairs-revised) rlhf dataset.
|
19 |
Training in French also improves the model in English, surpassing the performances of its base model.
|
20 |
-
128K context length
|
21 |
|
22 |
### OpenLLM Leaderboard
|
23 |
|
@@ -123,6 +123,8 @@ sequences = pipeline(
|
|
123 |
print(sequences[0]['generated_text'])
|
124 |
```
|
125 |
|
|
|
|
|
126 |
### Limitations
|
127 |
|
128 |
The Chocolatine model is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance.
|
|
|
17 |
DPO fine-tuned of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) (3.82B params)
|
18 |
using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/jpacifico/french-orca-dpo-pairs-revised) rlhf dataset.
|
19 |
Training in French also improves the model in English, surpassing the performances of its base model.
|
20 |
+
*The model supports 128K context length*.
|
21 |
|
22 |
### OpenLLM Leaderboard
|
23 |
|
|
|
123 |
print(sequences[0]['generated_text'])
|
124 |
```
|
125 |
|
126 |
+
* **4-bit quantized version** is available here : [jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M-GGUF)
|
127 |
+
|
128 |
### Limitations
|
129 |
|
130 |
The Chocolatine model is a quick demonstration that a base model can be easily fine-tuned to achieve compelling performance.
|