Upload MixtralForCausalLM

config.json

@@ -6,24 +6,25 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 512,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 3579,
+  "intermediate_size": 14336,
   "max_position_embeddings": 32768,
   "model_type": "mixtral",
   "num_attention_heads": 32,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 2,
   "num_key_value_heads": 8,
-  "num_local_experts": 4,
+  "num_local_experts": 8,
   "output_router_logits": false,
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.40.0"
 }

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bddee030eaebf61b1f46ab24345f8c71651303d48b46953438b203d6064e9e7
+size 4920052720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0071d9895ea0a5742ee2a9f08b4f04744397db92f403d781f67aa86dac6b4835
+size 4865559920

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd5705ffaffaed1f7762f53a8cce53a93ba9e3f15524412fef89856e3c4be79
+size 2873149136

model.safetensors.index.json

@@ -0,0 +1,72 @@
+{
+  "metadata": {
+    "total_size": 12658753536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}