Commit
•
b5aba93
1
Parent(s):
55893ee
Push model using huggingface_hub.
Browse files- README.md +42 -0
- added_tokens.json +3 -0
- config.json +28 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +56 -0
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- transformers
|
6 |
+
- reinforcement-learning
|
7 |
+
---
|
8 |
+
|
9 |
+
# TRL Model
|
10 |
+
|
11 |
+
This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
|
12 |
+
guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
|
13 |
+
|
14 |
+
## Usage
|
15 |
+
|
16 |
+
To use this model for inference, first install the TRL library:
|
17 |
+
|
18 |
+
```bash
|
19 |
+
python -m pip install trl
|
20 |
+
```
|
21 |
+
|
22 |
+
You can then generate text as follows:
|
23 |
+
|
24 |
+
```python
|
25 |
+
from transformers import pipeline
|
26 |
+
|
27 |
+
generator = pipeline("text-generation", model="damienbenveniste//var/folders/qj/lfvfq6590q5fn7hnwx6c29k80000gn/T/tmpi3wg7drx/damienbenveniste/mistral-ppo")
|
28 |
+
outputs = generator("Hello, my llama is cute")
|
29 |
+
```
|
30 |
+
|
31 |
+
If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
|
32 |
+
|
33 |
+
```python
|
34 |
+
from transformers import AutoTokenizer
|
35 |
+
from trl import AutoModelForCausalLMWithValueHead
|
36 |
+
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained("damienbenveniste//var/folders/qj/lfvfq6590q5fn7hnwx6c29k80000gn/T/tmpi3wg7drx/damienbenveniste/mistral-ppo")
|
38 |
+
model = AutoModelForCausalLMWithValueHead.from_pretrained("damienbenveniste//var/folders/qj/lfvfq6590q5fn7hnwx6c29k80000gn/T/tmpi3wg7drx/damienbenveniste/mistral-ppo")
|
39 |
+
|
40 |
+
inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
|
41 |
+
outputs = model(**inputs, labels=inputs["input_ids"])
|
42 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "damienbenveniste/mistral-supervised",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"max_length": 512,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 4,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 32000,
|
19 |
+
"padding_side": "left",
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"sliding_window": 768,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 512,
|
6 |
+
"pad_token_id": 32000,
|
7 |
+
"transformers_version": "4.35.2"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883cee707da1249523d4b9366967a0f215c5ee2ee3bd377cb5425f975e5a02c3
|
3 |
+
size 338200972
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<pad>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"additional_special_tokens": [],
|
37 |
+
"bos_token": "<s>",
|
38 |
+
"clean_up_tokenization_spaces": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"legacy": true,
|
41 |
+
"max_length": 30000,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_to_multiple_of": null,
|
44 |
+
"pad_token": "<pad>",
|
45 |
+
"pad_token_type_id": 0,
|
46 |
+
"paddind_side": "left",
|
47 |
+
"padding_side": "left",
|
48 |
+
"sp_model_kwargs": {},
|
49 |
+
"spaces_between_special_tokens": false,
|
50 |
+
"stride": 0,
|
51 |
+
"tokenizer_class": "LlamaTokenizer",
|
52 |
+
"truncation_side": "right",
|
53 |
+
"truncation_strategy": "longest_first",
|
54 |
+
"unk_token": "<unk>",
|
55 |
+
"use_default_system_prompt": false
|
56 |
+
}
|