Upload MistralForCausalLM

config.json

@@ -1,39 +1,24 @@
 {
   "_name_or_path": "./checkpoints/YuisekinAI-mistral-1.1B",
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "MistralForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 24,
-  "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 1024,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.39.2",
   "use_cache": true,

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.39.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a171919e275660be035290e494999ea5d1006684ed30262724a3ce408decde10
-size 1419322880
+oid sha256:44440e8ac8d858ee081e62fee7a55d4a818f206627edc3829af75ca909f51607
+size 4699339248