Upload folder using huggingface_hub

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+datasets:
+  - mrfakename/basic-math-10m
+language:
+  - en
+base_model:
+  - SupraLabs/Supra-50M-Reasoning
+pipeline_tag: text-generation
+tags:
+  - supra
+  - cpu
+  - 50m
+  - reasoning
+model-index:
+  - name: MathSupra
+    results:
+      - task:
+          type: text-generation
+        dataset:
+          name: GSM8K
+          type: openai/gsm8k
+          split: test
+        metrics:
+          - name: GSM8K (0-Shot)
+            type: extractive_match
+            value: 1.0
+        source:
+          name: Open SLM Leaderboard
+          url: https://huggingface.co
+---
+
+# MathSupra 50M Reasoning
+
+MathSupra is a fine tune of Supra-50M-reasoning designed for math, it was fine tuned on 25k subset of mrfakename/basic-math-10m for 1 epoch.
+MathSupra was fixed multiple times to be smarter.
+### Evaluation Metrics Summary
+- **GSM8K 0-Shot Accuracy**: 1.00% evaluated across standardized community slices tracked on the AxiomicLabs Open SLM Leaderboard.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1408,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 2,
+  "transformers_version": "5.10.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c972b83b447e08b168e3cb916778f82eb276bf1152216737718f300909c29e19
+size 207157136

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4514acba621378a387e41f3be62f024e4bd5d14c08a46e35f86ec8cf83ea4728
+size 5649