fixed the HuggingFace Inference API on the model page https://huggingface.co/matlok/tinyllama-cinder-openhermes-32k
Browse files
README.md
CHANGED
|
@@ -12,14 +12,6 @@ This model was merged with the following HuggingFace TinyLlama models using ties
|
|
| 12 |
- Tensoic/TinyLlama-1.1B-3T-openhermes
|
| 13 |
- Josephgflowers/TinyLlama-3T-Cinder-v1.3
|
| 14 |
|
| 15 |
-
## Why does the Inference API on HuggingFace not work for this merged model?
|
| 16 |
-
|
| 17 |
-
The included [merge python script](https://huggingface.co/matlok/tinyllama-cinder-openhermes-32k/blob/main/run-tiny-merge.py) does not contain the **LlamaTokenizerFast** tokenizer. This means the HuggingFace Inference API will not work. The tokenizer to use with this model is:
|
| 18 |
-
|
| 19 |
-
```
|
| 20 |
-
TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 21 |
-
```
|
| 22 |
-
|
| 23 |
## How do I fine-tune this model?
|
| 24 |
|
| 25 |
Please refer to the Unsloth fine-tuning guide for:
|
|
|
|
| 12 |
- Tensoic/TinyLlama-1.1B-3T-openhermes
|
| 13 |
- Josephgflowers/TinyLlama-3T-Cinder-v1.3
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## How do I fine-tune this model?
|
| 16 |
|
| 17 |
Please refer to the Unsloth fine-tuning guide for:
|