Trained with Unsloth

README.md

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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Locutusque/TinyMistral-248M",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pad_token_id": 32002,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "unsloth_version": "2025.2.15",
+  "use_cache": true,
+  "vocab_size": 32005
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 32002,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a64bff5bbd5a0e9f6982a75a07989549a4a517a6bcad7329a850d39c31bb36
+size 496060688