End of training
Browse files- README.md +5 -2
- config.json +1 -1
README.md
CHANGED
|
@@ -2,11 +2,14 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: ondevicellm/tinyllama_moe
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: tinyllama_moe_sft_ultrachat-slimorca
|
| 12 |
results: []
|
|
@@ -17,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# tinyllama_moe_sft_ultrachat-slimorca
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [ondevicellm/tinyllama_moe](https://huggingface.co/ondevicellm/tinyllama_moe) on the
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 1.1526
|
| 23 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: ondevicellm/tinyllama_moe
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
- generated_from_trainer
|
| 10 |
datasets:
|
| 11 |
+
- HuggingFaceH4/ultrachat_200k
|
| 12 |
+
- ondevicellm/SlimOrca
|
| 13 |
model-index:
|
| 14 |
- name: tinyllama_moe_sft_ultrachat-slimorca
|
| 15 |
results: []
|
|
|
|
| 20 |
|
| 21 |
# tinyllama_moe_sft_ultrachat-slimorca
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [ondevicellm/tinyllama_moe](https://huggingface.co/ondevicellm/tinyllama_moe) on the HuggingFaceH4/ultrachat_200k and the ondevicellm/SlimOrca datasets.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 1.1526
|
| 26 |
|
config.json
CHANGED
|
@@ -28,6 +28,6 @@
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.36.2",
|
| 31 |
-
"use_cache":
|
| 32 |
"vocab_size": 32000
|
| 33 |
}
|
|
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.36.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
"vocab_size": 32000
|
| 33 |
}
|