Text Generation
Transformers
Safetensors
PyTorch
English
llama
facebook
meta
llama-3
100K+ context length
LoRA
Theta Scaling
question answering
Norm & Embed Trained
Big Patents
instruct
question answering
merged
chat
8B
research
science
RoPE
long context
conversational
text-generation-inference
Inference Endpoints
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,18 @@ tags:
|
|
| 12 |
- LoRA
|
| 13 |
- Theta Scaling
|
| 14 |
- question answering
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
pipeline_tag: text-generation
|
| 16 |
extra_gated_prompt: >-
|
| 17 |
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
|
|
@@ -244,6 +256,14 @@ inference:
|
|
| 244 |
stop:
|
| 245 |
- <|end_of_text|>
|
| 246 |
- <|eot_id|>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
---
|
| 248 |
|
| 249 |
## Model Details
|
|
|
|
| 12 |
- LoRA
|
| 13 |
- Theta Scaling
|
| 14 |
- question answering
|
| 15 |
+
- 'Norm & Embed Trained '
|
| 16 |
+
- Big Patents
|
| 17 |
+
- instruct
|
| 18 |
+
- 'question answering '
|
| 19 |
+
- 'merged '
|
| 20 |
+
- 'chat '
|
| 21 |
+
- 8B
|
| 22 |
+
- research
|
| 23 |
+
- science
|
| 24 |
+
- RoPE
|
| 25 |
+
- long context
|
| 26 |
+
- conversational
|
| 27 |
pipeline_tag: text-generation
|
| 28 |
extra_gated_prompt: >-
|
| 29 |
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
|
|
|
|
| 256 |
stop:
|
| 257 |
- <|end_of_text|>
|
| 258 |
- <|eot_id|>
|
| 259 |
+
datasets:
|
| 260 |
+
- RMT-team/babilong
|
| 261 |
+
- facebook/babi_qa
|
| 262 |
+
- RMT-team/babilong-1k-samples
|
| 263 |
+
- Trelis/big_patent_100k_characters
|
| 264 |
+
metrics:
|
| 265 |
+
- accuracy
|
| 266 |
+
- perplexity
|
| 267 |
---
|
| 268 |
|
| 269 |
## Model Details
|