End of training
Browse files- README.md +6 -2
- config.json +1 -1
README.md
CHANGED
|
@@ -1,11 +1,15 @@
|
|
| 1 |
---
|
| 2 |
base_model: ondevicellm/tinyllama_moe_v2
|
| 3 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- trl
|
| 5 |
- sft
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
-
-
|
| 9 |
model-index:
|
| 10 |
- name: tinyllama_moe_sft_routeraux_ep3
|
| 11 |
results: []
|
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# tinyllama_moe_sft_routeraux_ep3
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [ondevicellm/tinyllama_moe_v2](https://huggingface.co/ondevicellm/tinyllama_moe_v2) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 1.2954
|
| 22 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: ondevicellm/tinyllama_moe_v2
|
| 3 |
tags:
|
| 4 |
+
- alignment-handbook
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
- trl
|
| 9 |
- sft
|
| 10 |
- generated_from_trainer
|
| 11 |
datasets:
|
| 12 |
+
- HuggingFaceH4/ultrachat_200k
|
| 13 |
model-index:
|
| 14 |
- name: tinyllama_moe_sft_routeraux_ep3
|
| 15 |
results: []
|
|
|
|
| 20 |
|
| 21 |
# tinyllama_moe_sft_routeraux_ep3
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [ondevicellm/tinyllama_moe_v2](https://huggingface.co/ondevicellm/tinyllama_moe_v2) on the HuggingFaceH4/ultrachat_200k dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 1.2954
|
| 26 |
|
config.json
CHANGED
|
@@ -28,6 +28,6 @@
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.37.0",
|
| 31 |
-
"use_cache":
|
| 32 |
"vocab_size": 32000
|
| 33 |
}
|
|
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.37.0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
"vocab_size": 32000
|
| 33 |
}
|