Upload MixtralForCausalLM

config.json

@@ -1,28 +1,30 @@
 {
-  "_name_or_path": "google/gemma-2b-it",
+  "_name_or_path": "TitanML/tiny-mixtral",
   "architectures": [
-    "GemmaForCausalLM"
+    "MixtralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_size": 2048,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 16384,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 1,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 131072,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.39.0.dev0",
   "use_cache": true,
-  "vocab_size": 256024
+  "vocab_size": 32024
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.39.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99592e16a7a298dd9f7592d8b996ee81aed23dac2acdf520b17815b1096d7906
+size 494028608