Update README.md
Browse files
README.md
CHANGED
|
@@ -32,26 +32,6 @@ Supervised fine-tuning with dataset:
|
|
| 32 |
- candenizkocak/code-alpaca-297k
|
| 33 |
- yahma/alpaca-cleaned
|
| 34 |
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
# Uploaded model
|
| 38 |
-
|
| 39 |
-
- **Developed by:** EpistemeAI
|
| 40 |
-
- **License:** apache-2.0
|
| 41 |
-
- **Finetuned from model :** EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v2.2a
|
| 42 |
-
|
| 43 |
-
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 44 |
-
|
| 45 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
# Guardrail/Moderation guide:
|
| 49 |
-
For guardrailing and moderating prompts against indirect/direct prompt injections and jailbreaking, please follow the SentinelShield AI GitHub repository:
|
| 50 |
-
[SentinelShield AI](https://github.com/tomtyiu/SentinelShieldAI)
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
# Model Card for Fireball-12B
|
| 56 |
|
| 57 |
The Heavy fine-tuned Mistral-Nemo-Base-2407 Large Language Model (LLM) is a pretrained generative text model of 12B parameters trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
|
|
@@ -77,6 +57,11 @@ Mistral Nemo is a transformer model, with the following architecture choices:
|
|
| 77 |
- **Vocabulary size:** 2**17 ~= 128k
|
| 78 |
- **Rotary embeddings (theta = 1M)**
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
#### Demo
|
| 81 |
|
| 82 |
After installing `mistral_inference`, a `mistral-demo` CLI command should be available in your environment.
|
|
@@ -155,4 +140,14 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
| 155 |
journal = {GitHub repository},
|
| 156 |
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
| 157 |
}
|
| 158 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
- candenizkocak/code-alpaca-297k
|
| 33 |
- yahma/alpaca-cleaned
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
# Model Card for Fireball-12B
|
| 36 |
|
| 37 |
The Heavy fine-tuned Mistral-Nemo-Base-2407 Large Language Model (LLM) is a pretrained generative text model of 12B parameters trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
|
|
|
|
| 57 |
- **Vocabulary size:** 2**17 ~= 128k
|
| 58 |
- **Rotary embeddings (theta = 1M)**
|
| 59 |
|
| 60 |
+
# Guardrail/Moderation guide:
|
| 61 |
+
For guardrailing and moderating prompts against indirect/direct prompt injections and jailbreaking, please follow the SentinelShield AI GitHub repository:
|
| 62 |
+
[SentinelShield AI](https://github.com/tomtyiu/SentinelShieldAI)
|
| 63 |
+
|
| 64 |
+
|
| 65 |
#### Demo
|
| 66 |
|
| 67 |
After installing `mistral_inference`, a `mistral-demo` CLI command should be available in your environment.
|
|
|
|
| 140 |
journal = {GitHub repository},
|
| 141 |
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
| 142 |
}
|
| 143 |
+
```
|
| 144 |
+
|
| 145 |
+
# Uploaded model
|
| 146 |
+
|
| 147 |
+
- **Developed by:** EpistemeAI
|
| 148 |
+
- **License:** apache-2.0
|
| 149 |
+
- **Finetuned from model :** EpistemeAI/Fireball-Mistral-Nemo-Base-2407-sft-v2.2a
|
| 150 |
+
|
| 151 |
+
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 152 |
+
|
| 153 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|