Update README.md
Browse files
README.md
CHANGED
|
@@ -3,5 +3,19 @@ datasets:
|
|
| 3 |
- WizardLM/WizardLM_evol_instruct_V2_196k
|
| 4 |
- HuggingFaceH4/ultrachat_200k
|
| 5 |
library_name: transformers
|
| 6 |
-
pipeline_tag:
|
| 7 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- WizardLM/WizardLM_evol_instruct_V2_196k
|
| 4 |
- HuggingFaceH4/ultrachat_200k
|
| 5 |
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
---
|
| 8 |
+
# Model Card for Mistral-7B-Evol-Ultrachat
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
|
| 12 |
+
### Model Description
|
| 13 |
+
|
| 14 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 15 |
+
Conversational model based on Mistral-7B. Trained using QLoRA + SFT on a RTX 3060. Uses the Mistral prompt format:
|
| 16 |
+
|
| 17 |
+
`[INST] Using this information : {context} answer the Question : {query} [/INST]`
|
| 18 |
+
|
| 19 |
+
- **Developed by:** dylan9n
|
| 20 |
+
- **Model type:** Conversational, Text Generation
|
| 21 |
+
- **Finetuned from model [optional]:** Mistral-7B
|