Upload SFT model (loss=0.3815)

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+library_name: peft
+base_model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit
+tags:
+- sft
+- lora
+- qwen2
+- adaptive-learning
+- multi-level
+- cmrl
+license: apache-2.0
+---
+
+# CMRL Adaptive Generator
+
+Multi-level adaptive generator trained with SFT (Supervised Fine-Tuning) for the C-MRL (Contrastive Multi-Resolution Learning) project.
+
+## Model Description
+
+This model adapts explanations to different difficulty levels:
+- **Novice**: 6th grade level, simple analogies
+- **Intermediate**: College student level
+- **Expert**: Technical/professional explanations
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base Model | unsloth/Qwen2-1.5B-Instruct-bnb-4bit |
+| LoRA Rank | 32 |
+| LoRA Alpha | 64 |
+| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
+| Epochs | 10 |
+| Learning Rate | 0.0002 |
+| Final Loss | 0.3815 |
+
+## Usage
+
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    "Ishaank18/cmrl-adaptive-generator",
+    max_seq_length=2048,
+    load_in_4bit=True,
+)
+FastLanguageModel.for_inference(model)
+
+# Generate
+prompt = "Instruct: You are an adaptive tutor.\nExplain photosynthesis to a 6th grader.\nOutput:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Intended Use
+
+Educational content generation at multiple difficulty levels. Part of the CMRL RAG pipeline with hierarchical retrieval.
+
+## Citation
+
+If you use this model, please cite:
+```
+@misc{cmrl-adaptive-generator,
+  author = {CMRL Project},
+  title = {Multi-Level Adaptive Generator},
+  year = {2024},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/Ishaank18/cmrl-adaptive-generator}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2-1.5B-Instruct-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175ae4366b9d0e67fe9fc4f9c77256be6775fa49e67c66b36b94be9689f942b8
+size 147770496

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

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 %}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6f32fb0a832e7efb2c2de5e805c8aaaf43e933c191ffc8d7cb56b176e0f11b
+size 11418364

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}