Push model using huggingface_hub.

README.md

@@ -0,0 +1,43 @@
+---
+license: apache-2.0
+tags:
+- trl
+- ppo
+- transformers
+- reinforcement-learning
+---
+
+# TRL Model
+
+This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
+ guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
+
+## Usage
+
+To use this model for inference, first install the TRL library:
+
+```bash
+python -m pip install trl
+```
+
+You can then generate text as follows:
+
+```python
+from transformers import pipeline
+
+generator = pipeline("text-generation", model="baek26//tmp/tmpxpk4iypn/baek26/wiki_asp-educational_institution_6506_bart-base")
+outputs = generator("Hello, my llama is cute")
+```
+
+If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
+
+```python
+from transformers import AutoTokenizer
+from trl import AutoModelForCausalLMWithValueHead
+
+tokenizer = AutoTokenizer.from_pretrained("baek26//tmp/tmpxpk4iypn/baek26/wiki_asp-educational_institution_6506_bart-base")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("baek26//tmp/tmpxpk4iypn/baek26/wiki_asp-educational_institution_6506_bart-base")
+
+inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
+outputs = model(**inputs, labels=inputs["input_ids"])
+```

config.json

@@ -0,0 +1,49 @@
+{
+  "exp_name": "rlqaf",
+  "seed": 0,
+  "log_with": null,
+  "task_name": null,
+  "model_name": "facebook/bart-base",
+  "query_dataset": "imdb",
+  "reward_model": "sentiment-analysis:lvwerra/distilbert-imdb",
+  "remove_unused_columns": true,
+  "tracker_kwargs": {},
+  "accelerator_kwargs": {},
+  "project_kwargs": {},
+  "tracker_project_name": "trl",
+  "push_to_hub_if_best_kwargs": {},
+  "steps": 20000,
+  "learning_rate": 1.41e-06,
+  "adap_kl_ctrl": true,
+  "init_kl_coef": 0.2,
+  "kl_penalty": "kl",
+  "target": 6,
+  "horizon": 10000,
+  "gamma": 0.9,
+  "lam": 0.95,
+  "cliprange": 0.2,
+  "cliprange_value": 0.2,
+  "vf_coef": 0.1,
+  "batch_size": 1,
+  "forward_batch_size": null,
+  "mini_batch_size": 1,
+  "gradient_accumulation_steps": 1,
+  "world_size": 1,
+  "ppo_epochs": 4,
+  "max_grad_norm": null,
+  "optimize_cuda_cache": null,
+  "optimize_device_cache": false,
+  "early_stopping": true,
+  "target_kl": 1,
+  "compare_steps": 1,
+  "ratio_threshold": 10.0,
+  "use_score_scaling": false,
+  "use_score_norm": false,
+  "score_clip": null,
+  "whiten_rewards": false,
+  "is_encoder_decoder": true,
+  "is_peft_model": false,
+  "backward_batch_size": 1,
+  "global_backward_batch_size": 1,
+  "global_batch_size": 1
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabbb90ad4e949002da08d462fadee84ca16fc02585651e40810423114d18c46
+size 557915872

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}