End of training
Browse files- README.md +4 -1
- config.json +26 -0
README.md
CHANGED
@@ -2,10 +2,13 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
9 |
model-index:
|
10 |
- name: mistral-poe-10p-detach
|
11 |
results: []
|
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# mistral-poe-10p-detach
|
18 |
|
19 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: nan
|
22 |
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
base_model: mistralai/Mistral-7B-v0.1
|
10 |
+
datasets:
|
11 |
+
- HuggingFaceH4/ultrachat_200k
|
12 |
model-index:
|
13 |
- name: mistral-poe-10p-detach
|
14 |
results: []
|
|
|
19 |
|
20 |
# mistral-poe-10p-detach
|
21 |
|
22 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: nan
|
25 |
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.39.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|