Update README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ license: apache-2.0
|
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
-
dragon-red-
|
10 |
|
11 |
DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production quality use in RAG scenarios.
|
12 |
|
@@ -31,10 +31,10 @@ For test run results (and good indicator of target use cases), please see the fi
|
|
31 |
<!-- Provide a longer summary of what this model is. -->
|
32 |
|
33 |
- **Developed by:** llmware
|
34 |
-
- **Model type:**
|
35 |
- **Language(s) (NLP):** English
|
36 |
- **License:** Apache 2.0
|
37 |
-
- **Finetuned from model:**
|
38 |
|
39 |
## Uses
|
40 |
|
@@ -69,16 +69,16 @@ Any model can provide inaccurate or incomplete information, and should be used i
|
|
69 |
|
70 |
## How to Get Started with the Model
|
71 |
|
72 |
-
The fastest way to get started with
|
73 |
|
74 |
-
from transformers import AutoTokenizer, AutoModelForCausalLM
|
75 |
-
tokenizer = AutoTokenizer.from_pretrained("dragon-red-
|
76 |
-
model = AutoModelForCausalLM.from_pretrained("dragon-red-
|
77 |
|
78 |
|
79 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
80 |
|
81 |
-
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
|
82 |
|
83 |
The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
|
84 |
|
@@ -87,15 +87,14 @@ The BLING model was fine-tuned with closed-context samples, which assume general
|
|
87 |
|
88 |
To get the best results, package "my_prompt" as follows:
|
89 |
|
90 |
-
my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
|
91 |
|
92 |
|
93 |
|
94 |
## Model Card Contact
|
|
|
|
|
95 |
|
96 |
-
Darren Oberst & llmware team
|
97 |
-
|
98 |
-
Please reach out anytime if you are interested in this project!
|
99 |
|
100 |
|
101 |
|
|
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
+
dragon-red-pajama-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a RedPajama-INCITE-7B base model.
|
10 |
|
11 |
DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production quality use in RAG scenarios.
|
12 |
|
|
|
31 |
<!-- Provide a longer summary of what this model is. -->
|
32 |
|
33 |
- **Developed by:** llmware
|
34 |
+
- **Model type:** RedPajama-INCITE-7B
|
35 |
- **Language(s) (NLP):** English
|
36 |
- **License:** Apache 2.0
|
37 |
+
- **Finetuned from model:** RedPajama-INCITE-7B
|
38 |
|
39 |
## Uses
|
40 |
|
|
|
69 |
|
70 |
## How to Get Started with the Model
|
71 |
|
72 |
+
The fastest way to get started with dRAGon is through direct import in transformers:
|
73 |
|
74 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
75 |
+
tokenizer = AutoTokenizer.from_pretrained("dragon-red-pajama-7b-v0")
|
76 |
+
model = AutoModelForCausalLM.from_pretrained("dragon-red-pajama-7b-v0")
|
77 |
|
78 |
|
79 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
80 |
|
81 |
+
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
|
82 |
|
83 |
The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
|
84 |
|
|
|
87 |
|
88 |
To get the best results, package "my_prompt" as follows:
|
89 |
|
90 |
+
my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
|
91 |
|
92 |
|
93 |
|
94 |
## Model Card Contact
|
95 |
+
Darren Oberst
|
96 |
+
llmware
|
97 |
|
|
|
|
|
|
|
98 |
|
99 |
|
100 |
|