MicroGPT-2 SFT: safetensors (Qwen3 layout) + GGUF f16 and q8_0

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+microgpt2-f16.gguf filter=lfs diff=lfs merge=lfs -text
+microgpt2-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1 @@
+{{- bos_token -}}{%- set offset = 0 -%}{%- if messages and messages[0]['role'] == 'system' -%}{%- if messages|length > 1 and messages[1]['role'] == 'user' -%}{{- '<|im_start|>user\n' + messages[0]['content'] + '\n\n' + messages[1]['content'] + '<|im_end|>' -}}{%- set offset = 2 -%}{%- else -%}{{- '<|im_start|>user\n' + messages[0]['content'] + '<|im_end|>' -}}{%- set offset = 1 -%}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if loop.index0 >= offset -%}{{- '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' -}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|im_start|>assistant\n' -}}{%- endif -%}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "model_type": "qwen3",
+  "vocab_size": 49152,
+  "hidden_size": 1280,
+  "intermediate_size": 3328,
+  "num_hidden_layers": 25,
+  "num_attention_heads": 10,
+  "num_key_value_heads": 5,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "rope_scaling": null,
+  "max_position_embeddings": 1024,
+  "tie_word_embeddings": true,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "use_cache": true,
+  "sliding_window": null,
+  "use_sliding_window": false,
+  "torch_dtype": "float32",
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0
+}

microgpt2-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8fcf8f0c8dad481de9c03ed26d3f450efd2739f386478b0318ff0940d9dc90
+size 1012637696

microgpt2-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6f3aa3e28c41a700c11d1c45b81c569abd932b8ce07391e168b4299315b039
+size 538935296

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64e58bf835a56cf42b86c6156f2487bf121f96d8bfacc9c7ee49cf0880824cb
+size 2021448328

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152,
+  "add_bos_token": false,
+  "add_eos_token": false
+}