Upload MistralForCausalLM

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/jupyter/Nucleus-1B-alpha-1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfba841ebb408dea3037ec92b8b10b134791538b3cc656667a414de7267ad2c
+size 899696312

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce491e8c0cd8107ccea201a9e81add205368e7f2544e35c3bebdb5de0b7463bd
+size 989890680

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3ed345995de780fa46cf25e11913c70c06934d6fe7ff20b64d7188d3539bd2
+size 379609640

model.safetensors.index.json

@@ -0,0 +1,46 @@
+{
+  "metadata": {
+    "total_size": 2269192192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-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.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}