Upload 22 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+models/qlora-adapter/checkpoint-19/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/qlora-adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,19 @@
 ---
-title: Plainscript
-emoji: 🏆
-colorFrom: yellow
-colorTo: indigo
+title: PlainScript Medical Rewriter
+emoji: 🩺
+colorFrom: green
+colorTo: pink
 sdk: gradio
-sdk_version: 6.22.0
-python_version: '3.12'
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# PlainScript — Patient-Friendly Medical Rewriter
+
+Fine-tuned Qwen2-1.5B (QLoRA) that rewrites dense medical text into plain
+language. Toggle shows base vs fine-tuned output side by side.
+
+Trained on Cochrane plain-language summary pairs. Drafts for review only —
+not medical advice.

app.py

@@ -0,0 +1,295 @@
+"""
+Patient-Friendly Medical Rewriter — Gradio web app.
+
+Loads Qwen2-1.5B-Instruct with the trained LoRA adapter and exposes a
+before/after comparison UI. The base ("before") and fine-tuned ("after")
+outputs come from a single PeftModel by toggling the adapter on and off
+with disable_adapter(), which keeps memory low enough for HF Spaces'
+free CPU tier.
+
+Entry point for Hugging Face Spaces (Gradio SDK looks for app.py).
+"""
+
+import os
+
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+
+MODEL_ID = "Qwen/Qwen2-1.5B-Instruct"
+ADAPTER_DIR = os.environ.get("ADAPTER_DIR", "models/qlora-adapter")
+
+SYSTEM_PROMPT = (
+    "You are a medical text simplifier. Rewrite the following medical text "
+    "into plain language that a patient with no medical background can "
+    "understand. Preserve all key findings and conclusions. Do not add "
+    "information not present in the original text."
+)
+
+EXAMPLES = [
+    "A meta-analysis of randomized controlled trials demonstrated a "
+    "statistically significant reduction in glycated hemoglobin (HbA1c) "
+    "levels (mean difference -0.5%, 95% CI -0.7 to -0.3, p<0.001) in "
+    "patients receiving the intervention compared to placebo.",
+    "The systematic review found moderate-certainty evidence that cognitive "
+    "behavioural therapy reduces the severity of chronic insomnia symptoms "
+    "compared with treatment as usual, measured by the Pittsburgh Sleep "
+    "Quality Index at 8 weeks post-intervention.",
+    "Prophylactic administration of low-molecular-weight heparin was "
+    "associated with reduced incidence of venous thromboembolism in "
+    "post-operative orthopaedic patients (RR 0.50, 95% CI 0.33 to 0.76), "
+    "though with a concomitant increase in minor bleeding events.",
+]
+
+
+def _device() -> str:
+    """Pick the best available device."""
+    if torch.cuda.is_available():
+        return "cuda"
+    if torch.backends.mps.is_available():
+        return "mps"
+    return "cpu"
+
+
+print("Loading model (this can take a minute on first launch)...")
+DEVICE = _device()
+DTYPE = torch.float16 if DEVICE in ("cuda", "mps") else torch.float32
+
+tokenizer = AutoTokenizer.from_pretrained(ADAPTER_DIR, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+
+_base = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID, dtype=DTYPE, trust_remote_code=True
+)
+# Keep the adapter separate (not merged) so we can toggle it on/off.
+model = PeftModel.from_pretrained(_base, ADAPTER_DIR)
+model = model.to(DEVICE)
+model.eval()
+print(f"Model loaded on {DEVICE}.")
+
+
+def _generate(text: str, max_new_tokens: int = 400) -> str:
+    """Run one generation with the current adapter state."""
+    messages = [
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user", "content": text},
+    ]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    inputs = tokenizer(prompt, return_tensors="pt").to(DEVICE)
+    with torch.no_grad():
+        out = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.1,
+        )
+    gen = out[0][inputs["input_ids"].shape[1]:]
+    return tokenizer.decode(gen, skip_special_tokens=True).strip()
+
+
+def rewrite(text: str):
+    """
+    Produce base ('before') and fine-tuned ('after') rewrites.
+
+    The base output is generated with the adapter disabled; the fine-tuned
+    output with it enabled — same weights in memory, toggled per call.
+    """
+    if not text or not text.strip():
+        return "", "Please paste some medical text above to see the rewrite."
+
+    with model.disable_adapter():
+        before = _generate(text)
+    after = _generate(text)
+    return before, after
+
+
+# ---------------------------------------------------------------------------
+# UI
+# ---------------------------------------------------------------------------
+
+CUSTOM_CSS = """
+:root {
+  --teal: #0EA5A4;
+  --teal-deep: #0B7C7B;
+  --coral: #FB7185;
+  --ink: #0F172A;
+  --mint: #F0FDFA;
+  --card: rgba(255, 255, 255, 0.72);
+}
+
+.gradio-container {
+  background: linear-gradient(135deg, #F0FDFA 0%, #E0F2FE 50%, #FCE7F3 100%);
+  background-size: 400% 400%;
+  animation: bgshift 18s ease infinite;
+  font-family: 'Inter', -apple-system, BlinkMacSystemFont, sans-serif !important;
+  max-width: 1100px !important;
+  margin: auto !important;
+}
+
+@keyframes bgshift {
+  0% { background-position: 0% 50%; }
+  50% { background-position: 100% 50%; }
+  100% { background-position: 0% 50%; }
+}
+
+/* floating medical stickers */
+#sticker-layer {
+  position: fixed;
+  inset: 0;
+  pointer-events: none;
+  z-index: 0;
+  overflow: hidden;
+}
+.sticker {
+  position: absolute;
+  font-size: 2.4rem;
+  opacity: 0.14;
+  animation: float 14s ease-in-out infinite;
+}
+.sticker:nth-child(1) { left: 6%;  top: 18%; animation-delay: 0s;   }
+.sticker:nth-child(2) { left: 84%; top: 12%; animation-delay: 2s;   }
+.sticker:nth-child(3) { left: 12%; top: 72%; animation-delay: 4s;   }
+.sticker:nth-child(4) { left: 78%; top: 68%; animation-delay: 1s;   }
+.sticker:nth-child(5) { left: 46%; top: 8%;  animation-delay: 3s;   }
+.sticker:nth-child(6) { left: 90%; top: 44%; animation-delay: 5s;   }
+.sticker:nth-child(7) { left: 3%;  top: 45%; animation-delay: 2.5s; }
+
+@keyframes float {
+  0%, 100% { transform: translateY(0) rotate(-4deg); }
+  50%      { transform: translateY(-26px) rotate(4deg); }
+}
+
+.hero {
+  position: relative;
+  z-index: 1;
+  text-align: center;
+  padding: 26px 16px 6px;
+}
+.hero h1 {
+  font-size: 2.5rem;
+  font-weight: 800;
+  letter-spacing: -0.02em;
+  color: var(--ink);
+  margin: 0;
+}
+.hero h1 .accent { color: var(--teal-deep); }
+.hero p {
+  color: #475569;
+  font-size: 1.05rem;
+  margin: 10px auto 0;
+  max-width: 620px;
+}
+
+/* ECG signature line */
+.ecg {
+  width: 220px; height: 40px; margin: 14px auto 0; display: block;
+}
+.ecg path {
+  fill: none; stroke: var(--coral); stroke-width: 2.5;
+  stroke-dasharray: 300; stroke-dashoffset: 300;
+  animation: trace 2.2s linear infinite;
+}
+@keyframes trace { to { stroke-dashoffset: -300; } }
+
+.panel-card, .gr-box, .gr-panel { position: relative; z-index: 1; }
+
+/* Output panels */
+#before_box textarea {
+  background: rgba(255,255,255,0.6) !important;
+  border-left: 4px solid #94A3B8 !important;
+}
+#after_box textarea {
+  background: rgba(240,253,250,0.9) !important;
+  border-left: 4px solid var(--teal) !important;
+  font-weight: 500;
+}
+
+button.primary, #go_btn {
+  background: linear-gradient(135deg, var(--teal) 0%, var(--teal-deep) 100%) !important;
+  border: none !important;
+  color: white !important;
+  font-weight: 600 !important;
+}
+
+.disclaimer {
+  text-align: center; color: #64748B; font-size: 0.82rem;
+  margin-top: 18px; position: relative; z-index: 1;
+}
+"""
+
+STICKERS_HTML = """
+<div id="sticker-layer">
+  <div class="sticker">&#129658;</div>
+  <div class="sticker">&#128138;</div>
+  <div class="sticker">&#10084;&#65039;</div>
+  <div class="sticker">&#129656;</div>
+  <div class="sticker">&#128137;</div>
+  <div class="sticker">&#127973;</div>
+  <div class="sticker">&#129701;</div>
+</div>
+"""
+
+HERO_HTML = """
+<div class="hero">
+  <h1>Plain<span class="accent">Script</span></h1>
+  <p>Paste a dense medical abstract and watch it turn into language a patient
+     can actually understand. See the model before and after fine-tuning.</p>
+  <svg class="ecg" viewBox="0 0 220 40">
+    <path d="M0,20 L60,20 L70,20 L78,4 L88,36 L98,20 L120,20 L128,12 L136,28 L146,20 L220,20"/>
+  </svg>
+</div>
+"""
+
+
+def build_app() -> gr.Blocks:
+    """Construct the Gradio Blocks interface."""
+    with gr.Blocks(css=CUSTOM_CSS, title="PlainScript — Medical Rewriter") as app:
+        gr.HTML(STICKERS_HTML)
+        gr.HTML(HERO_HTML)
+
+        with gr.Row():
+            input_text = gr.Textbox(
+                label="Medical text",
+                placeholder="Paste a medical abstract or clinical summary here…",
+                lines=6,
+                elem_id="input_box",
+            )
+
+        go_btn = gr.Button("Rewrite it", variant="primary", elem_id="go_btn")
+
+        with gr.Row():
+            before_box = gr.Textbox(
+                label="Before  ·  base Qwen2-1.5B",
+                lines=9,
+                interactive=False,
+                elem_id="before_box",
+            )
+            after_box = gr.Textbox(
+                label="After  ·  fine-tuned on Cochrane",
+                lines=9,
+                interactive=False,
+                elem_id="after_box",
+            )
+
+        gr.Examples(examples=EXAMPLES, inputs=input_text, label="Try an example")
+
+        gr.HTML(
+            '<div class="disclaimer">Drafts for review only — not medical '
+            "advice. Outputs may contain errors and must be checked by a "
+            "qualified professional before any patient-facing use.</div>"
+        )
+
+        go_btn.click(fn=rewrite, inputs=input_text, outputs=[before_box, after_box])
+
+    return app
+
+
+if __name__ == "__main__":
+    demo = build_app()
+    demo.launch(server_name="0.0.0.0", server_port=7860)

models/qlora-adapter/README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
+model_name: qlora-adapter
+tags:
+- base_model:adapter:Qwen/Qwen2-1.5B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for qlora-adapter
+
+This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```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="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.20.0
+- TRL: 1.9.2
+- Transformers: 5.14.1
+- Pytorch: 2.11.0+cu128
+- Datasets: 5.0.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

models/qlora-adapter/adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

models/qlora-adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eee72a1dda2d7e14715bb53d63e8ac69604b71fcfe9a25e51f7498e1df35b0
+size 8746152

models/qlora-adapter/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

models/qlora-adapter/checkpoint-19/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-1.5B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

models/qlora-adapter/checkpoint-19/adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

models/qlora-adapter/checkpoint-19/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eee72a1dda2d7e14715bb53d63e8ac69604b71fcfe9a25e51f7498e1df35b0
+size 8746152

models/qlora-adapter/checkpoint-19/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

models/qlora-adapter/checkpoint-19/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69be2bca19da23ec8f5095c89d0619bab7c6f2e66fd282bb9f498630b701f73c
+size 17624139

models/qlora-adapter/checkpoint-19/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83052e4995106c6cd2889c5d71cb82eeb5554622bfaf6c04ea5d2b42200522e1
+size 14645

models/qlora-adapter/checkpoint-19/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05c64baded779c44674cf60fea5d030392afceb752a7adf9b93c35bb717462d
+size 1465

models/qlora-adapter/checkpoint-19/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
+size 11418262

models/qlora-adapter/checkpoint-19/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

models/qlora-adapter/checkpoint-19/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 19,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 25,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2987258504294400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

models/qlora-adapter/checkpoint-19/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d74734ce9cb9bcc14d79fa44b836130442b41dc2e3dbb85c24097b9b0b9e291
+size 5713

models/qlora-adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
+size 11418262

models/qlora-adapter/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

models/qlora-adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d74734ce9cb9bcc14d79fa44b836130442b41dc2e3dbb85c24097b9b0b9e291
+size 5713

requirements.txt

@@ -0,0 +1,5 @@
+torch>=2.1.0
+transformers>=4.40.0
+peft>=0.10.0
+accelerate>=0.30.0
+gradio>=4.44.0