初始化项目，由ModelHub XC社区提供模型

Model: harsh762011/numinao14-new
Source: Original Platform

.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

README.md

@@ -0,0 +1,85 @@
+---
+license: cc-by-nc-3.0
+base_model: unsloth/phi-4-mini-reasoning
+tags:
+  - text-generation-inference
+  - transformers
+  - unsloth
+  - phi-4
+language:
+  - en
+---
+
+# Phi-4 Mini Reasoning – JEE Mathematics Finetuned Model
+
+A new version of the model present at `harsh762011/numiano14`.
+
+# Uploaded Finetuned Model
+
+- **Developed by:** Harsh Srivastava
+- **License:** cc-by-nc-3.0
+- **Finetuned from model:** unsloth/phi-4-mini-reasoning
+
+This Phi-4 model was trained faster using Unsloth and Hugging Face TRL.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+---
+
+# Description
+
+This model is a finetuned version of Phi-4 Mini Reasoning designed for solving JEE-level mathematics problems.
+
+The model is optimized for:
+- Step-by-step mathematical reasoning
+- Symbolic problem solving
+- Competitive exam-style question solving
+
+---
+
+# Training Dataset
+
+Total samples used: 500k+ filtered mathematics and reasoning samples.
+
+The training pipeline focuses on JEE-level mathematical difficulty using keyword-based dataset filtering.
+
+## Sources
+
+- AI-MO/NuminaMath-CoT — 293k samples (2 epochs)
+- AI-MO/NuminaMath-TIR — 68,850 samples
+- MetaMathQA — 70k samples
+- TIGER-Lab MathInstruct — 125,220 samples
+- PhysicsWallahAI JEE Main 2025 (Jan) — 182 samples
+- PhysicsWallahAI JEE Main 2025 (Apr) — 169 samples
+- MMLU High School Mathematics — 78 samples
+- MMLU College Mathematics — 50 samples
+- MMLU Abstract Algebra — 25 samples
+
+---
+
+# Training Details
+
+- **Base model:** Phi-4 Mini Reasoning
+- **Framework:** Unsloth + Hugging Face TRL
+- **Training method:** LoRA finetuning
+- **Sequence length:** 2048
+- **Optimizer:** AdamW 8bit
+
+---
+
+# Intended Purpose
+
+The model is designed for:
+
+- JEE mathematics reasoning
+- Step-by-step mathematical explanations
+- Competitive exam problem solving
+- Mathematical chain-of-thought reasoning
+
+---
+
+# Limitations
+
+- The model may still generate incorrect mathematical reasoning.
+- Outputs should be verified for high-stakes usage.
+- The model is still under active improvement and continued training.

chat_template.jinja

@@ -0,0 +1 @@
+{{ '<|system|>Your name is Phi, an AI math expert developed by Microsoft.' }}{% for message in messages %}{% if message['role'] == 'system' %} {{ message['content'] }}{% if 'tools' in message and message['tools'] is not none %}{{ '<|tool|>' + message['tools'] + '<|/tool|>' }}{% endif %}{% endif %}{% endfor %}{{ '<|end|>' }}{% for message in messages %}{% if message['role'] != 'system' %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}

config.json

@@ -0,0 +1,143 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 199999,
+  "dtype": "float16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "ignore_keys_at_rope_validation": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 200018,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "original_max_position_embeddings": 4096,
+    "partial_rotary_factor": 0.75,
+    "rope_theta": 10000.0,
+    "rope_type": "longrope",
+    "short_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "type": "longrope"
+  },
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 200064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": [
+    200020,
+    199999
+  ],
+  "max_length": 131072,
+  "pad_token_id": 200018,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4117e3cc56ce828be0ac45c084764ed96d2b05f0687beb0e6e951792e5094e85
+size 7672066056

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167ad4184f68275a61856ea519ba94485dc594ad7648468decaa495987c0b15c
+size 15524657

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "max_length": 1024,
+  "model_max_length": 131072,
+  "pad_token": "<|endofprompt|>",
+  "padding_side": "left",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "�"
+}