Upload model

config.json

@@ -5,8 +5,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 90000,
-  "eos_token_id": 90001,
+  "bos_token_id": 16000,
+  "eos_token_id": 16001,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -19,35 +19,6 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "config_groups": {
-      "group_0": {
-        "input_activations": null,
-        "output_activations": null,
-        "targets": [
-          "Linear"
-        ],
-        "weights": {
-          "actorder": null,
-          "block_structure": null,
-          "dynamic": false,
-          "group_size": null,
-          "num_bits": 8,
-          "observer": "minmax",
-          "observer_kwargs": {},
-          "strategy": "channel",
-          "symmetric": true,
-          "type": "int"
-        }
-      }
-    },
-    "format": "pack-quantized",
-    "global_compression_ratio": 1.4619490646162168,
-    "ignore": [],
-    "kv_cache_scheme": null,
-    "quant_method": "compressed-tensors",
-    "quantization_status": "compressed"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -61,5 +32,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.0.dev0",
   "use_cache": true,
-  "vocab_size": 90002
+  "vocab_size": 16002
 }

model-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad7bfbbc4af2329771ae80b392f84f56a2135eb6034140b2885dfcc58a753dd0
+oid sha256:52ba4109a3588dceeeaa6a0e95afbce89cfce1959f8fb0f26c2a2c9aaace711d
 size 2127524202

model-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1f2decb4df6334cf086aa124ebbf54055753674021c9626a7597fe7b9fc76e
-size 1592416566
+oid sha256:1f3444171638be798a157c39429f4c481aa06cb2741274cfe97e6ebd2be73f79
+size 1134584970

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 3719696208
+        "total_size": 3261864772
     },
     "weight_map": {
         "model.layers.0.self_attn.q_proj.weight.shape": "model-00001.safetensors",

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|end_of_text|>"
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a26f4c94b5df1ea07103f220db22a49948724ee7eaabcf1e57cf124c715c28a
-size 5559269
+oid sha256:1815b9fadc431c29dfcb0bb41b6f488388f0d23f7ab41270ce7ea08ca9000b42
+size 839048

tokenizer_config.json

@@ -1 +1 @@
-{"added_tokens_decoder": {"90000": {"content": "<|begin_of_text|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "90001": {"content": "<|end_of_text|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "bos_token": "<|begin_of_text|>", "clean_up_tokenization_spaces": true, "eos_token": "<|end_of_text|>", "model_input_names": ["input_ids", "attention_mask"], "model_max_length": 131072, "pad_token": "<|end_of_text|>", "tokenizer_class": "PreTrainedTokenizerFast"}
+{"added_tokens_decoder": {"16000": {"content": "<|begin_of_text|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "16001": {"content": "<|end_of_text|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "bos_token": "<|begin_of_text|>", "clean_up_tokenization_spaces": true, "eos_token": "<|end_of_text|>", "model_input_names": ["input_ids", "attention_mask"], "model_max_length": 131072, "tokenizer_class": "PreTrainedTokenizerFast"}