Upload folder using huggingface_hub

config.json

@@ -0,0 +1,102 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 32768,
+    "hidden_size": 4096,
+    "intermediate_size": 14336,
+    "num_hidden_layers": 32,
+    "num_attention_heads": 32,
+    "sliding_window": null,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "use_cache": true,
+    "rope_theta": 1000000.0,
+    "attention_dropout": 0.0,
+    "torch_dtype": "float16",
+    "tie_word_embeddings": false,
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "_name_or_path": "/home/austin/disk1/text-generation-webui/models/Mistral-7B-Instruct-v0.2",
+    "transformers_version": "4.37.0",
+    "model_type": "mistral",
+    "quantization_config": {
+        "quant_method": "aqlm",
+        "nbits_per_codebook": 16,
+        "num_codebooks": 1,
+        "out_group_size": 1,
+        "in_group_size": 8,
+        "linear_weights_not_to_quantize": [
+            "model.layers.0.input_layernorm.weight",
+            "model.layers.0.post_attention_layernorm.weight",
+            "model.layers.1.input_layernorm.weight",
+            "model.layers.1.post_attention_layernorm.weight",
+            "model.layers.2.input_layernorm.weight",
+            "model.layers.2.post_attention_layernorm.weight",
+            "model.layers.3.input_layernorm.weight",
+            "model.layers.3.post_attention_layernorm.weight",
+            "model.layers.4.input_layernorm.weight",
+            "model.layers.4.post_attention_layernorm.weight",
+            "model.layers.5.input_layernorm.weight",
+            "model.layers.5.post_attention_layernorm.weight",
+            "model.layers.6.input_layernorm.weight",
+            "model.layers.6.post_attention_layernorm.weight",
+            "model.layers.7.input_layernorm.weight",
+            "model.layers.7.post_attention_layernorm.weight",
+            "model.layers.8.input_layernorm.weight",
+            "model.layers.8.post_attention_layernorm.weight",
+            "model.layers.9.input_layernorm.weight",
+            "model.layers.9.post_attention_layernorm.weight",
+            "model.layers.10.input_layernorm.weight",
+            "model.layers.10.post_attention_layernorm.weight",
+            "model.layers.11.input_layernorm.weight",
+            "model.layers.11.post_attention_layernorm.weight",
+            "model.layers.12.input_layernorm.weight",
+            "model.layers.12.post_attention_layernorm.weight",
+            "model.layers.13.input_layernorm.weight",
+            "model.layers.13.post_attention_layernorm.weight",
+            "model.layers.14.input_layernorm.weight",
+            "model.layers.14.post_attention_layernorm.weight",
+            "model.layers.15.input_layernorm.weight",
+            "model.layers.15.post_attention_layernorm.weight",
+            "model.layers.16.input_layernorm.weight",
+            "model.layers.16.post_attention_layernorm.weight",
+            "model.layers.17.input_layernorm.weight",
+            "model.layers.17.post_attention_layernorm.weight",
+            "model.layers.18.input_layernorm.weight",
+            "model.layers.18.post_attention_layernorm.weight",
+            "model.layers.19.input_layernorm.weight",
+            "model.layers.19.post_attention_layernorm.weight",
+            "model.layers.20.input_layernorm.weight",
+            "model.layers.20.post_attention_layernorm.weight",
+            "model.layers.21.input_layernorm.weight",
+            "model.layers.21.post_attention_layernorm.weight",
+            "model.layers.22.input_layernorm.weight",
+            "model.layers.22.post_attention_layernorm.weight",
+            "model.layers.23.input_layernorm.weight",
+            "model.layers.23.post_attention_layernorm.weight",
+            "model.layers.24.input_layernorm.weight",
+            "model.layers.24.post_attention_layernorm.weight",
+            "model.layers.25.input_layernorm.weight",
+            "model.layers.25.post_attention_layernorm.weight",
+            "model.layers.26.input_layernorm.weight",
+            "model.layers.26.post_attention_layernorm.weight",
+            "model.layers.27.input_layernorm.weight",
+            "model.layers.27.post_attention_layernorm.weight",
+            "model.layers.28.input_layernorm.weight",
+            "model.layers.28.post_attention_layernorm.weight",
+            "model.layers.29.input_layernorm.weight",
+            "model.layers.29.post_attention_layernorm.weight",
+            "model.layers.30.input_layernorm.weight",
+            "model.layers.30.post_attention_layernorm.weight",
+            "model.layers.31.input_layernorm.weight",
+            "model.layers.31.post_attention_layernorm.weight",
+            "model.embed_tokens.weight",
+            "model.norm.weight",
+            "lm_head.weight"
+        ]
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33455d76c466ab493ca43abdda959b13560353eeb7fbe59981499f7252487a61
+size 2507540438

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}