Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen3
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "chat_template": "{%- set last_message = messages[-1] -%}\n{%- if last_message.role == \"user\" -%}\n{{- '<|problem_start|>\n' + last_message.content + '<|problem_end|>\n' -}}\n{%- elif last_message.role == \"assistant\" -%}\n{%- for message in messages -%}\n{%- if message.role == \"user\" -%}\n{{- '<|problem_start|>\n' + message.content + '<|problem_end|>\n' -}}\n{%- elif message.role == \"assistant\" -%}\n{{- '<|formatted_problem_start|>\n' + message.content + '<|formatted_problem_end|>\n' -}}\n{%- else -%}\n{{- raise('Unknown role: ' + message.role) -}}\n{%- endif -%}\n{%- endfor -%}\n{%- else -%}\n{{- raise('Unsupported role: ' + last_message.role) -}}\n{%- endif -%}\n{%- if add_generation_prompt and last_message.role == \"user\" -%}\n{{- '<|formatted_problem_start|>\n' -}}\n{%- endif -%}",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.5.5",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151673
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_length": 32768,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151654,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b3b452b2e1653a21eb6faa5f6b61c2ee93221b36903fcdd143db4956cb5786
+size 3440108360