Ursa Minor v0.3

README.md

@@ -1,99 +1,202 @@
 ---
-license: apache-2.0
-datasets:
-- mlabonne/FineTome-100k
-language:
-- en
-base_model:
-- Qwen/Qwen2.5-1.5B-Instruct
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
 ---
-# Ursa Minor v0.2
 
-[![Apache License 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+# Model Card for Model ID
 
-A reasoning-enhanced language model distilled from Google's Gemini 2.0 Flash Thinking into Qwen 1.5B. Version 0.2 shows significant improvement over v0.1, with enhanced reasoning capabilities and coherent text generation.
+<!-- Provide a quick summary of what the model is/does. -->
 
-## Model Overview
 
-Ursa Minor v0.2 is designed to mimic the chain-of-thought reasoning patterns of Google's Gemini 2.0 Flash Thinking model. The model demonstrates step-by-step reasoning for problem-solving tasks and provides explanations with visible thought processes.
 
-### Specifications
+## Model Details
 
-- **Base Model**: Qwen 1.5B, a 1.5 billion parameter decoder-only transformer model
-- **Context Window**: 4096 tokens
-- **Tokenizer**: Same as Qwen 1.5B
-- **Parameter Count**: 1.5B
+### Model Description
 
-## Model Access
+<!-- Provide a longer summary of what this model is. -->
 
-The model is available on Hugging Face in two versions:
 
-- Original: [https://huggingface.co/Kaileh57/Ursa_Minor](https://huggingface.co/Kaileh57/Ursa_Minor)
-- Quantized: [https://huggingface.co/mradermacher/Ursa_Minor-GGUF](https://huggingface.co/mradermacher/Ursa_Minor-GGUF)
 
-## Usage Example
+- **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]
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+### Model Sources [optional]
 
-# Load the model and tokenizer
-model_path = "Kaileh57/Ursa_Minor"
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(model_path)
+<!-- Provide the basic links for the model. -->
 
-# Create a reasoning prompt
-prompt = """Think through this step by step:
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
-How would you determine if a number is a prime number? Design an algorithm and trace through it for the number 29.
+## 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. -->
 
-# Format the prompt
-formatted_prompt = tokenizer.apply_chat_template([
-    {"role": "system", "content": "You are a helpful assistant."},
-    {"role": "user", "content": prompt}
-], tokenize=False)
+### Direct Use
 
-# Generate a response
-inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-print(response)
-```
+[More Information Needed]
 
-## Training Methodology
+### Downstream Use [optional]
 
-The model was created using knowledge distillation techniques, where Qwen 1.5B (student model) was trained to mimic the reasoning patterns of Gemini 2.0 Flash Thinking (teacher model). This approach transfers reasoning capabilities from the larger teacher model to the smaller student model.
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
-The distillation process used one of two primary methods:
-- **Logit-based distillation**: Where the student model is trained to produce similar output probability distributions as the teacher
-- **Hidden states-based distillation**: Where the internal representations of the student model are aligned with those of the teacher
+[More Information Needed]
 
-## Intended Use
+### Out-of-Scope Use
 
-This model is designed to:
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-- Demonstrate step-by-step reasoning for problem-solving tasks
-- Break down complex problems into manageable components
-- Provide explanations with visible thought processes
-- Support educational scenarios where seeing the reasoning process is beneficial
+[More Information Needed]
 
-## Limitations
+## Bias, Risks, and Limitations
 
-- **Reasoning Depth**: May not achieve the same reasoning depth as Gemini due to parameter count differences
-- **Scope**: Reasoning capabilities are limited to the types of problems it was exposed to during training
-- **Mathematical Accuracy**: May make calculation errors on complex mathematical problems
-- **Hallucination**: May occasionally generate plausible-sounding but incorrect reasoning steps
-- **Size Constraints**: At 1.5B parameters, has less capacity than larger models like Gemini
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-## Ethical Considerations
+[More Information Needed]
 
-- The model may inherit biases present in both the Qwen base model and the Gemini responses
-- Reasoning chains may occasionally reinforce stereotypes or contain subtle biases
-- The model should not be used for critical decision-making without human oversight
-- Responses should be verified for correctness, especially for domain-specific reasoning
+### Recommendations
 
-## License
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-This project is licensed under the Apache License 2.0.
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "bias": "none",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6baae6a259181b49035e2e4339724a6e3551050c8b61dda9de0036ef8e49bb
+size 73911112

added_tokens.json

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

special_tokens_map.json

@@ -1,20 +1,20 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1
-size 7028043
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -1,43 +1,43 @@
-{
-  "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,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+{
+  "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,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}