Upload Open Reason small CPU causal LM (not 1B)

README.md

@@ -0,0 +1,34 @@
+---
+language:
+  - en
+license: apache-2.0
+library_name: transformers
+tags:
+  - open-reason
+  - causal-lm
+  - cpu
+datasets:
+  - theworker02/open-reason
+base_model: gpt2-scratch
+---
+
+# Open Reason small (CPU)
+
+This is a **small** GPT-2-style causal LM trained from scratch on the
+Open Reason SFT split. It is **not** a 1B model and is **not**
+`theworker02/open-reason-1b`.
+
+- Parameters (approx): 1334016
+- Steps: 200
+- Backend: cpu-host
+- CUDA used: False
+- Rows: 2348
+- Final loss: 6.095415115356445
+
+Hardware: CPU (Docker when available). AMD GPU training is not used.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tok = AutoTokenizer.from_pretrained("theworker02/open-reason-small")
+model = AutoModelForCausalLM.from_pretrained("theworker02/open-reason-small")
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 128,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 128,
+  "pad_token_id": 1,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.10.2",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db31aae3e0d0b741acbf8e624c054c36d7e053f7bc05f98ba0404732e4198a6
+size 5341104

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

train_metrics.json

@@ -0,0 +1,27 @@
+{
+  "smoke": false,
+  "cuda": false,
+  "backend": "cpu-host",
+  "architecture": "gpt2-scratch",
+  "param_count": 1334016,
+  "n_layer": 4,
+  "n_embd": 128,
+  "n_head": 4,
+  "steps": 200,
+  "rows": 2348,
+  "final_loss": 6.095415115356445,
+  "losses_tail": [
+    5.3571391105651855,
+    5.712825298309326,
+    5.500826835632324,
+    5.698274612426758,
+    5.465966701507568,
+    5.777740001678467,
+    5.92188024520874,
+    5.687778472900391,
+    5.9522929191589355,
+    6.095415115356445
+  ],
+  "hub_id_if_uploaded": "theworker02/open-reason-small",
+  "note": "Small CPU causal LM. Not open-reason-1b. Not AMD GPU."
+}