Upload MistralForCausalLM

config.json

@@ -1,37 +1,23 @@
 {
-  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-01_15-15-06",
-  "activation_function": "gelu_new",
+  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-02_14-51-37",
   "architectures": [
-    "GPT2LMHeadModel"
+    "MistralForCausalLM"
   ],
-  "attn_pdrop": 0.0,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 864,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 20,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.0,
-  "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": 2382,
+  "max_position_embeddings": 1024,
+  "model_type": "mistral",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "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": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.34.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86fbefd2dab45a47244c54a712981e73d5d489a38e8c1312a08683921922da66
-size 724595976
+oid sha256:2ead740ef0d552952652fd924fb5460937530329026b07c0a663d5bcf393e5f2
+size 743784040