Model save

README.md

@@ -6,31 +6,30 @@ tags:
 - generated_from_trainer
 - trl
 - sft
-license: apache-2.0
-datasets:
-- OpenAssistant/oasst1
+licence: license
 ---
 
-# notHumpback-M0
+# Model Card for notHumpback-M0
 
-This model follows the Humpback architecture, proposed in the paper [Self-Alignment with Instruction Backtranslation](https://arxiv.org/pdf/2308.06259) 
-by Li et al.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-It represents the "seed model", which is trained on a small amount of gold data and then
-used to score the instruction-response pairs 
-generated by the ["backward model"](https://huggingface.co/Alepach/notHumpback-Myx).
+## Quick start
 
-Humpback uses instruction backtranslation on a web corpus to generate input-output pairs (self-augmentation), 
-creating a richer dataset for fine-tuning models without the need for additional manual annotation.
-The model then iteratively curates the created dataset, scoring the pairs by quality, and is then finetuned on the resulting subset 
-of all pairs with the highest possible score (self-curation).
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Alepach/notHumpback-M0", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
 
-Varying from the original paper, this model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B).
-It has been trained using [TRL](https://github.com/huggingface/trl).
 
-The dataset used to train this model has been sampled from the [oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset. 
-To enable the model to judge and score the generated pairs, the model undergoes basic instruction-tuning on the input-output 
-pairs contained in the dataset.
+
+This model was trained with SFT.
 
 ### Framework versions
 
@@ -42,18 +41,7 @@ pairs contained in the dataset.
 
 ## Citations
 
-Original paper:
 
-```bibtex
-@misc{li2023selfalignment,
-    title={Self-Alignment with Instruction Backtranslation},
-    author={Xian Li and Ping Yu and Chunting Zhou and Timo Schick and Luke Zettlemoyer and Omer Levy and Jason Weston and Mike Lewis},
-    year={2023},
-    eprint={2308.06259},
-    archivePrefix={arXiv},
-    primaryClass={cs.CL}
-}
-```
 
 Cite TRL as:
     

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffe3b2120490b45a390cc9048ce99f3602a62df7ad04f0b4755b183f57d5caa
+oid sha256:d06535c06f6b2aad587adc2d53e896c4a7fb309bf104507225784cd0992c731f
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f780b5a8be7f7da8f94d1315c3d896b3bfa658fb665eb4e67c9a3b3d709f080d
+oid sha256:4b7873c402b3ded5eaf4837e845eb6fcd63611690605207852cfc21df2810bed
 size 1459729952

special_tokens_map.json

@@ -13,11 +13,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|finetune_right_pad_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|finetune_right_pad_id|>"
 }

tokenizer_config.json

@@ -2053,15 +2053,11 @@
   "chat_template": "{{- bos_token }}\n{% set ns = namespace(system_message='') %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n        {% set ns.system_message = message['content'].strip() %}\n    {%- elif message['role'] == 'user' %}\n        {{- '<|start_header_id|>user<|end_header_id|>' + ns.system_message + '\\n' + message['content'].strip() + '<|eot_id|>' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>' + message['content'] + '<|eot_id|>' }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
-  "max_length": 131072,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6058e7bbc92865f32405379f79f3236570d8717a003ddb1c256d6b3837479765
+oid sha256:949ffd2edc274bd55a1b61c4a8ad2fd6c7cd62b02414efc8a46b21604165e7e2
 size 5560