Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 vizuosense_ggml.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+vizuosense_ggml.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,22 +1,22 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "_name_or_path": "openlm-research/open_llama_3b_v2",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 3200,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 26,
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",

generation_config.json

@@ -2,8 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 32000,
-  "temperature": 0.9,
-  "top_p": 0.6,
+  "pad_token_id": 0,
   "transformers_version": "4.31.0"
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "bos_token": {
     "__type": "AddedToken",
     "content": "<s>",
@@ -16,8 +18,8 @@
     "rstrip": false,
     "single_word": false
   },
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": true,
+  "model_max_length": 2048,
   "pad_token": null,
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

vizuosense_ggml.Q2_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab30fe8f45e9a543d7fa3e562c1ce22ef8cff3eaa42aca0eb769606aa1151f7
-size 2825940672
+oid sha256:679ad823a20385323721ed052f8c6c23117c33b7a44e6586b56f0fd1320458d7
+size 2147988224

vizuosense_ggml.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5586362e3ab31511c96305917a4ce61d339b36b8c066bcee097a0909a09a3c0
+size 2187668224