Downloads · 30 days
115
0% of all-time downloads
rombodawg/LosslessMegaCoder-Falcon-40b-mini
LosslessMegaCoder-Falcon-40b-mini is a text generation model from rombodawg. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Please note this model was not trained on the rombodawg/LosslessMegaCodeTrainingV3MINI dataset, despite the name similarity. You can find the training data at the bottom of the model card labeled (megacode2-min100)
Downloads · 30 days
115
0% of all-time downloads
All-time downloads
28.7K
Public
Parameters
41.3B
82.6 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors82.6 GB · 100%
From the Hugging Face model README
This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evol_Uncensored dataset. The version of the dataset used for this model was filtered by removed any data with less than 100 tokens but plans for much more refined filtering are in the works
Prompt template:
multi-line:
<|im_start|>system
{system message}<|im_end|>
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>
Gpt4all template:
<|im_start|>system
"Below is an instruction that describes a task. Write a response that appropriately completes the request."
<|im_end|>
<|im_start|>user
"%1"<|im_end|>
<|im_start|>assistant
Oobagooba Text-Generation-Webui Template
<|im_start|>user
{User string}<|im_end|>
<|im_start|>assistant
{Bot string}<|im_end|>
<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n
<|im_start|>system
Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>
Current quantizations available:
The link for the full dataset is bellow:
Link for the filtered dataset used to make this model are bellow:
The original posting for this model was uploaded at the link bellow.