Upload MistralForCausalLM

config.json

@@ -1,28 +1,26 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
+  "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.37.2",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 38369
 }

generation_config.json

@@ -1,10 +1,7 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "max_length": 4096,
-  "pad_token_id": 0,
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.37.2",
+  "use_cache": false
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5b958e69193e8ddd6079344f728d1cb370809beff022ed61a1bfe37ea0b134
-size 4938985248
+oid sha256:76a179e74c9bd6cb72791a55cc985ca323e73a1408d65e426ded2b44f6ad809c
+size 4995337088

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2091994e27cfd683bad1aa18a67b25db35bdb06f18201f66669f7ab2ff2881c
-size 4947390768
+oid sha256:d8160f2ba59a21443b6041e34075a53fe45202b28dfa223456fb38c2b932dfb9
+size 4999819232

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b00db1905ff1b05dac589b377fdfe76f19f06a013d1ad5076a5e112b7eea82
-size 3590488736
+oid sha256:6dc632ed601eb7b77793b747ef61bfba35f1638cf3fab0c2638512da530204f7
+size 4592691112

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476831232
+    "total_size": 14587813888
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -23,24 +23,24 @@
     "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.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -140,24 +140,24 @@
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",