Add Sekai-1 chat model weights, tokenizer and How to use section

README.md

@@ -25,6 +25,36 @@ All scores are zero-shot. Sekai-1's scores were measured locally on the same tas
 **Pretraining:** 58.5B tokens of web, educational, math, code and conversation data, with a warmup-stable-decay schedule. The final ~12B tokens were a decay phase on a higher-quality mix.
 **Chat fine-tuning (SFT):** about 400M tokens of instruction following, everyday chat, short and long answers, summarizing and rewriting, code writing and code fixing, plus a small set of identity examples, so the model knows it is Sekai-1. It does not use chain-of-thought (a model this size doesn't benefit from it), and refusals were filtered out of the data.
 
+## How to use
+
+```bash
+pip install transformers torch
+```
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "8BitStudio/Sekai-1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+messages = [{"role": "user", "content": "Who are you?"}]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_dict=True, return_tensors="pt")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
+
+The model is small enough to run on a CPU. The default sampling settings (temperature 0.5, top-p 0.9, top-k 40, repetition penalty 1.1) are stored in `generation_config.json`; pass `do_sample=False` to `generate()` for deterministic answers.
+
+Sekai-1 uses the ChatML format:
+
+```
+<|im_start|>user
+What is the capital of France?<|im_end|>
+<|im_start|>assistant
+Paris<|im_end|>
+```
+
 ## Limitations
 
 Sekai-1 is a 95.6M-parameter model. It makes factual mistakes, loses track in long conversations, and is weak at multi-step reasoning and math beyond simple arithmetic. 

chat_template.jinja

@@ -0,0 +1,4 @@
+{{ bos_token }}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "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": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 23,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.15.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 24576,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32"
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    0
+  ],
+  "max_new_tokens": 512,
+  "min_p": 0.02,
+  "pad_token_id": 0,
+  "repetition_penalty": 1.1,
+  "temperature": 0.5,
+  "top_k": 40,
+  "top_p": 0.9,
+  "transformers_version": "5.15.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f959f9f068128c8dc3d15620f1eb9f785857548b5b57eaf36180f2630ea907
+size 382354208

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|reserved_0|>",
+    "<|reserved_1|>",
+    "<|reserved_2|>",
+    "<|reserved_3|>",
+    "<|reserved_4|>"
+  ],
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}