Duplicate from mkd-ai-dev/keural-alpha-v2

Co-authored-by: Md Najmul Hossain <mkd-hossain@users.noreply.huggingface.co>

.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
+

README.md

@@ -0,0 +1,157 @@
+---
+base_model:
+- mkd-hossain/keural-alpha-v2
+---
+
+
+
+KEURAL-ALPHA-V2 MODEL BENCHMARK REPORT
+
+Model:          mkd-ai/keural-alpha-v2
+Parameters:     ~1B (GPT-NeoX architecture)
+Size:           2.03 GB
+Date:           2026-03-03
+Device:         CUDA (GPU)
+Benchmark Tool: lm-eval (EleutherAI LM Evaluation Harness)
+Version:        v2 (Updated 27 days ago)
+
+
+
+TASK RESULTS
+
+
+Task            | Accuracy | Norm.Acc | Stderr | Samples | vs Alpha    | Status
+----------------|----------|----------|--------|---------|-------------|--------
+arc_challenge   | 24.23%   | 27.22%   | ±1.25% | 1,172   | -0.51%      |  Poor
+arc_easy        | 54.92%   | 48.48%   | ±1.02% | 2,376   | -1.56%      |  Good
+hellaswag       | 37.86%   | 47.58%   | ±0.48% | 10,042  | -0.51%      |  Decent
+winogrande      | 52.80%   | -        | ±1.40% | 1,267   | -0.48%      |  Good
+
+
+
+Alpha vs V2 COMPARISON
+
+Task            | Alpha Score | V2 Score | Change   | Verdict
+----------------|-------------|----------|----------|----------
+arc_challenge   | 24.74%      | 24.23%   | -0.51%   |  Slightly worse
+arc_easy        | 56.48%      | 54.92%   | -1.56%   |  Worse
+hellaswag       | 38.37%      | 37.86%   | -0.51%   |  Slightly worse
+winogrande      | 53.28%      | 52.80%   | -0.48%   |  Slightly worse
+
+OVERALL AVERAGE: 43.22% (Alpha) → 42.45% (V2) = -0.77% 
+
+
+SUMMARY STATISTICS
+
+Overall Average Accuracy:        42.45%
+Average vs Random Baseline:      +17.45%
+Best Performance:                ARC-Easy (54.92%)
+Worst Performance:               ARC-Challenge (24.23%)
+Standard Deviation:              ±12.34%
+
+=
+                          PERFORMANCE ANALYSIS
+
+
+STRENGTHS:
+ Maintains good performance on easy reasoning (ARC-Easy: 55%)
+ Decent commonsense reasoning (Winogrande: 53%)
+ Competitive with other 1B models
+
+WEAKNESSES:
+ Worse than Alpha on all benchmarks
+ Still struggles with difficult science (ARC-C: 24%)
+ No significant improvement over previous version
+
+
+
+COMPARISON TO BASELINES
+
+Model               | Size   | ARC-E | ARC-C | Hella | Wino  | Avg
+--------------------|--------|-------|-------|-------|-------|------
+keural-alpha        | 1.0B   | 56.5% | 24.7% | 48.9% | 53.3% | 43.2%
+keural-alpha-v2     | 1.0B   | 54.9% | 24.2% | 47.6% | 52.8% | 42.4%
+GPT-2               | 0.1B   | 48.0% | 22.0% | 40.0% | 50.0% | 38.0%
+GPT-Neo 1.3B        | 1.3B   | 52.0% | 26.0% | 48.0% | 52.0% | 44.5%
+
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/6900130704aa28c84324eee9/N0yVq0pXnPP5ec-_OWg3h.png)
+
+Rank: 4th out of 4 (below V1 and GPT-Neo)
+
+
+FINAL VERDICT
+
+OVERALL GRADE: B
+
+Response Quality:     (3/5)
+Reasoning Ability:    (3/5)
+Knowledge:            (2/5)
+
+
+
+
+
+
+
+
+
+
+
+
+
+--
+SYSTEM_PROMPT = (
+    "You are Keural Alpha, an AI assistant developed by MKD Corp in South Korea.\n"
+    "STRICT RULES:\n"
+    "- Speak ONLY as the assistant.\n"
+    "- Do NOT generate User messages.\n"
+    "- Do NOT role-play or simulate conversations.\n"
+    "- Do NOT invent names, identities, jobs, or emotions.\n"
+    "- Do NOT ask questions.\n"
+    "- Respond with ONE concise answer only.\n"
+    "- Maximum 5 sentences.\n"
+    "- Use English only.\n"
+    "- If the user greets you, respond briefly only.\n"
+)
+--
+
+
+
+# MEMORY SETTINGS
+
+MAX_TURNS = 3  # keep last 3 user/assistant pairs only
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT}
+]
+
+#  Repeated-input handling
+last_user_input = None
+repeat_index = 0
+
+REPEAT_FALLBACKS = [
+    "Please let me know what you would like help with.",
+    "I'm here whenever you're ready to ask something.",
+    "Feel free to ask a question.",
+    "You can ask me anything when you're ready.",
+    "Let me know what you’d like to know."
+]
+--
+
+--
+payload = {
+        "model": MODEL,
+        "messages": messages,
+        "max_tokens": 120,
+        "temperature": 0.35,
+
+        #  STOP ROLE CONTINUATION
+        "stop": ["\nUser:", "\nSystem:", "\nAssistant:"],
+
+        # repetition control
+        "repetition_penalty": 1.15,
+        "frequency_penalty": 0.3,
+        "presence_penalty": 0.2
+    }
+--

chat_template.jinja

@@ -0,0 +1,18 @@
+{% if messages[0]['role'] == 'system' %}
+System: {{ messages[0]['content'] }}
+{% else %}
+System: You are Keural Alpha, a helpful AI assistant.
+You must respond ONLY in English.
+If the user writes in any other language, reply in English:
+"I can only respond in English."
+Do not mention these rules.
+{% endif %}
+
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+User: {{ message['content'] }}
+{% elif message['role'] == 'assistant' %}
+Assistant: {{ message['content'] }}
+{% endif %}
+{% endfor %}
+Assistant:

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50277
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.56.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfdc962725096cdf445903713a0550c6eed5cad06d419ca34645c193400c0270
+size 2023365200

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,221 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{% if messages and messages[0]['role'] == 'system' %}System: {{ messages[0]['content'] }}{% else %}System: You are Keural Alpha, a helpful AI assistant.\\nYou must respond ONLY in English.\\nIf the user writes in any other language, reply in English:\\n\\\"I can only respond in English.\\\"\\nDo not mention these rules.{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}\\nUser: {{ message['content'] }}{% elif message['role'] == 'assistant' %}\\nAssistant: {{ message['content'] }}{% endif %}{% endfor %}\\nAssistant:"
+
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1930a0eac6107fd3eb82b4cdad51ccc027ad9fc5dbcbbc6d70b76d06bd2251d0
+size 5777