Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,7 @@ tags:
|
|
13 |
- safetersors
|
14 |
- pytorch
|
15 |
- coding
|
|
|
16 |
datasets:
|
17 |
- Replete-AI/code_bagel
|
18 |
---
|
@@ -47,21 +48,22 @@ https://huggingface.co/datasets/Replete-AI/code_bagel
|
|
47 |
|
48 |
## Uses
|
49 |
|
50 |
-
|
51 |
|
52 |
|
53 |
|
54 |
## Bias, Risks, and Limitations
|
55 |
|
56 |
-
it can some times produce a wrong
|
57 |
|
58 |
|
59 |
|
60 |
### Recommendations
|
61 |
|
62 |
-
NOTE:you shold have lm studio or ollama to use this model
|
|
|
|
|
63 |
|
64 |
-
IN LM-STUDIO:it is recommended to use this model with the defult lm-studio configration.
|
65 |
IN OLLAMA: we will be pushing the model soon to ollama.
|
66 |
|
67 |
|
@@ -72,7 +74,7 @@ model trained with unsloth.
|
|
72 |
|
73 |
### Training Data
|
74 |
|
75 |
-
the training dataset that i used: https://huggingface.co/datasets/
|
76 |
|
77 |
## IMPORTANT LINKS
|
78 |
|
@@ -82,7 +84,7 @@ LM-STUDIO: https://lmstudio.ai
|
|
82 |
|
83 |
llama3.1: instruct: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
|
84 |
|
85 |
-
dataset: https://huggingface.co/datasets/
|
86 |
|
87 |
|
88 |
### Results
|
|
|
13 |
- safetersors
|
14 |
- pytorch
|
15 |
- coding
|
16 |
+
- finetuned
|
17 |
datasets:
|
18 |
- Replete-AI/code_bagel
|
19 |
---
|
|
|
48 |
|
49 |
## Uses
|
50 |
|
51 |
+
This model is finetuned specifically for coding and it has a 131072 context lingth.
|
52 |
|
53 |
|
54 |
|
55 |
## Bias, Risks, and Limitations
|
56 |
|
57 |
+
it can some times produce a wrong answers.
|
58 |
|
59 |
|
60 |
|
61 |
### Recommendations
|
62 |
|
63 |
+
NOTE: you shold have lm studio or ollama to use this model
|
64 |
+
|
65 |
+
IN LM-STUDIO: it is recommended to use this model with the defult lm-studio configration.
|
66 |
|
|
|
67 |
IN OLLAMA: we will be pushing the model soon to ollama.
|
68 |
|
69 |
|
|
|
74 |
|
75 |
### Training Data
|
76 |
|
77 |
+
the training dataset that i used: https://huggingface.co/datasets/Replete-AI/code_bagel
|
78 |
|
79 |
## IMPORTANT LINKS
|
80 |
|
|
|
84 |
|
85 |
llama3.1: instruct: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
|
86 |
|
87 |
+
dataset: https://huggingface.co/datasets/Replete-AI/code_bagel
|
88 |
|
89 |
|
90 |
### Results
|