amirabdullah19852020 commited on
Commit
3292a22
1 Parent(s): dc87feb

Push model using huggingface_hub.

Browse files
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="amirabdullah19852020//tmp/tmpm5q6ykh8/amirabdullah19852020/pythia-160m_utility_reward")
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("amirabdullah19852020//tmp/tmpm5q6ykh8/amirabdullah19852020/pythia-160m_utility_reward")
38
+ model = AutoModelForCausalLMWithValueHead.from_pretrained("amirabdullah19852020//tmp/tmpm5q6ykh8/amirabdullah19852020/pythia-160m_utility_reward")
39
+
40
+ inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
41
+ outputs = model(**inputs, labels=inputs["input_ids"])
42
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-160m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.32.1",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 50304
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.32.1"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1f006d52baf746a6e60fb32d1c378b36720777e027c108e0469707c9179a76
3
+ size 649349269
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }