Upload 10 files

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "ifuseok/sft-solar-10.7b-v2.1",
+  "_name_or_path": "ifuseok/sft-solar-10.7b-v1.1",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -16,6 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 48,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
@@ -24,5 +24,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.34.1",
   "use_cache": false,
-  "vocab_size": 48000
+  "vocab_size": 32000
 }

generation_config.json

@@ -2,6 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 2,
   "transformers_version": "4.34.1",
   "use_cache": false
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f830cc5110f0120e577070e1fff6987a7b7bde0c314b760f6306a484cb31c98
-size 9990167144
+oid sha256:e88527c86783c60a55a7e42cfb6250721ab64f7adf3ccd99f4cb4ecade66e1d6
+size 9942981696

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7386e746505b5712108074be279554d85e97f70642f8bd92afe4b1cf0c8295ac
-size 9915718912
+oid sha256:915d1745a194f6628b932d4ac8e08d8df46bdbb667ad1da0f1abff885c5ddba1
+size 9999621616

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6151cdcc19178a2549e71d42bd5db34fdade0a80893821ab9b0266368cb935ff
-size 1819356784
+oid sha256:f0a8309a88b412642c68849aed72ad9e938834edac0646777b5262ebc1349766
+size 1520495544

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 21725192192
+    "total_size": 21463048192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -145,10 +145,10 @@
     "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.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.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -356,11 +356,11 @@
     "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
@@ -370,10 +370,10 @@
     "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,