yuchiz commited on
Commit
1d49a5e
1 Parent(s): e4f65da

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/lvwerra/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="yuchiz//srv/condor/execute/dir_58527/tmp2m7xrrvu/yuchiz/cache")
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("yuchiz//srv/condor/execute/dir_58527/tmp2m7xrrvu/yuchiz/cache")
38
+ model = AutoModelForCausalLMWithValueHead.from_pretrained("yuchiz//srv/condor/execute/dir_58527/tmp2m7xrrvu/yuchiz/cache")
39
+
40
+ inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
41
+ outputs = model(**inputs, labels=inputs["input_ids"])
42
+ ```
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "berkeley-nest/Starling-LM-7B-alpha",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059adfa837f7442af84b8617d6c63e075feeb29dea1a76d54ed33553c0a97dcf
3
+ size 27280152
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83b0983cd8cf84631a6b08d65e74a19d81f9e55439bf0477ccd155edec0d0b4
3
+ size 17471
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443