From 0f7f3865194d8c845e57531667351a81b7f21e57 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 14 Jun 2026 18:06:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: SeeYangZhi/Llama-3.2-1B-Sarcasm-Rewriter-Context Source: Original Platform --- .gitattributes | 36 ++++++++++++ README.md | 122 +++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 93 +++++++++++++++++++++++++++++++ config.json | 36 ++++++++++++ generation_config.json | 14 +++++ model.safetensors | 3 + tokenizer.json | 3 + tokenizer_config.json | 14 +++++ 8 files changed, 321 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..117029e --- /dev/null +++ b/README.md @@ -0,0 +1,122 @@ +--- +license: llama3.2 +base_model: meta-llama/Llama-3.2-1B-Instruct +tags: +- text-generation +- style-transfer +- sarcasm +- llama +language: +- en +pipeline_tag: text-generation +--- + +# Llama-3.2-1B-Sarcasm-Rewriter-Context + +A LoRA fine-tuned [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) that rewrites sarcastic news headlines as neutral, factual equivalents. Trained with **article body context** in the prompt during supervised fine-tuning, producing stronger sarcasm comprehension than headline-only training. + +Built by CS4248 Team 14 (NUS, AY2025/26 Semester 2) as part of a sarcasm style transfer research project. + +## Why this model + +Compared to the sibling [`Llama-3.2-1B-Sarcasm-Rewriter`](https://huggingface.co/SeeYangZhi/Llama-3.2-1B-Sarcasm-Rewriter) (headline-only training), this context-enhanced variant: + +- Lower perplexity (318 vs 378) +- Higher LLM-judged sarcasm removal score (4.96/5 vs 4.74/5) +- **Better meaning preservation** (4.32/5 vs 3.80/5) — the largest improvement +- Same near-perfect fluency (4.98/5) + +The training targets were generated by an LLM annotator that had access to the full article body, producing deeper rewrites than headline-only targets. The model learned to mimic these more faithful rewrites. + +## Task + +**Input**: A sarcastic news headline +**Output**: A non-sarcastic rewrite + +``` +Input: "Inconsiderate Wife Leaves Bathroom A Total Mess After Home Birth" +Output: "Mother of Two Gives Birth at Home" +``` + +## Training + +- **Base model**: [`meta-llama/Llama-3.2-1B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) (1.24B params) +- **Method**: LoRA (r=16, α=32, dropout=0.05) targeting `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` +- **Trainable parameters**: ~11.3M (0.9% of base) +- **Dataset**: 6,463 sarcastic→non-sarcastic headline pairs where article bodies were available. Targets generated by StepFun Step-3.5 Flash (LLM annotator with article body access), cross-validated by Nemotron. Split: `sar_to_non_context_enhanced` with body filter applied. +- **Prompt format (training)**: system prompt + user turn containing both the sarcastic headline AND the full article body as context +- **Loss**: Computed only on the assistant response tokens (target headline), not on the prompt +- **Training setup**: 3 epochs on H200 GPU, LR 2e-4 cosine, batch 4 × grad_accum 4, bfloat16, gradient checkpointing +- **Best checkpoint**: Epoch 1 (eval_loss 1.492) + +After training, the LoRA adapter was merged into the base weights via `merge_and_unload()`. + +## Usage — Recommended (headline-only prompt) + +Even though the model was trained with article bodies, **inference-time evaluation showed the model performs best with headline-only prompts**. Feeding article bodies at inference introduces hallucination from article content. Use this configuration in production: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "SeeYangZhi/Llama-3.2-1B-Sarcasm-Rewriter-Context" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id) + +messages = [ + { + "role": "system", + "content": ( + "You are a writing assistant. Rewrite sarcastic news headlines as neutral, " + "factual equivalents that preserve the core meaning without irony or mockery. " + "Respond with only the rewritten headline, no explanation." + ), + }, + { + "role": "user", + "content": ( + "Rewrite this sarcastic headline as a neutral, non-sarcastic news headline:\n\n" + "inconsiderate wife leaves bathroom a total mess after home birth" + ), + }, +] + +prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(prompt, return_tensors="pt") +outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False) +print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)) +``` + +## Usage — Alternative (with article body, matches training distribution) + +If you have the source article body available, you can pass it in the prompt. Note that evaluation showed this mode produces slightly worse outputs than headline-only due to body-distractor hallucination, so it is not recommended: + +```python +user_content = ( + "Rewrite this sarcastic headline as a neutral, non-sarcastic news headline.\n\n" + f"Headline: {sarcastic_headline}\n\n" + f"Article context:\n{article_body}" +) +``` + +## Evaluation + +Compared against 14 other models (BART variants, T5 variants, ablations, previous LLaMA) on a 2,857-sample held-out test split with 7 metrics. Key results vs previous headline-only variant: + +| Metric | Llama-context (this model) | Llama (previous) | +|---|---|---| +| Flip rate (classifier) | 22.5% | 21.9% | +| Semantic similarity | 0.679 | 0.656 | +| Perplexity (GPT-2) | **318** | 378 | +| LLM sarcasm removed | **4.96/5** | 4.74/5 | +| LLM meaning preserved | **4.32/5** | 3.80/5 | +| LLM fluency | 4.98/5 | 4.98/5 | + +Full per-metric numbers are published alongside the project webapp. + +## License + +This model is released under the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE). The model name starts with "Llama-" as required by Meta's terms. Built with Llama. + +## Citation + +If you use this model, please cite the underlying Llama 3.2 release and the NHDSD dataset. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1bad6a0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,93 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- if strftime_now is defined %} + {%- set date_string = strftime_now("%d %b %Y") %} + {%- else %} + {%- set date_string = "26 Jul 2024" %} + {%- endif %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {{- "<|eot_id|>" }} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..758d80f --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.5.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b88c287 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128009, + 128001, + 128008, + 128009 + ], + "pad_token_id": 128009, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4e614fd --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0059741a5524873f3a8c1f74ddffcc97788ce3c1fbe99c80c3db11b0b0490f61 +size 2471645608 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..bf19ce7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc +size 17210019 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b0c7368 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +}