Upload folder using huggingface_hub

config.json

@@ -64,7 +64,8 @@
     ],
     "quant_method": "gptq",
     "sym": true,
-    "true_sequential": true
+    "true_sequential": true,
+    "disable_exllama": false
   },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
@@ -75,4 +76,4 @@
   "transformers_version": "4.38.0.dev0",
   "use_cache": true,
   "vocab_size": 32000
-}
+}

quantize_config.json

@@ -0,0 +1,48 @@
+{
+  "bits": 4,
+  "dataset": "wikitext2",
+  "group_size": -1,
+  "damp_percent": 0.1,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "quant_method": "gptq",
+  "modules_in_block_to_quantize": [
+    [
+      "self_attn.k_proj",
+      "self_attn.v_proj",
+      "self_attn.q_proj"
+    ],
+    [
+      "self_attn.o_proj"
+    ],
+    [
+      "block_sparse_moe.experts.0.w1",
+      "block_sparse_moe.experts.1.w1",
+      "block_sparse_moe.experts.2.w1",
+      "block_sparse_moe.experts.3.w1",
+      "block_sparse_moe.experts.4.w1",
+      "block_sparse_moe.experts.5.w1",
+      "block_sparse_moe.experts.6.w1",
+      "block_sparse_moe.experts.7.w1",
+      "block_sparse_moe.experts.0.w3",
+      "block_sparse_moe.experts.1.w3",
+      "block_sparse_moe.experts.2.w3",
+      "block_sparse_moe.experts.3.w3",
+      "block_sparse_moe.experts.4.w3",
+      "block_sparse_moe.experts.5.w3",
+      "block_sparse_moe.experts.6.w3",
+      "block_sparse_moe.experts.7.w3"
+    ],
+    [
+      "block_sparse_moe.experts.0.w2",
+      "block_sparse_moe.experts.1.w2",
+      "block_sparse_moe.experts.2.w2",
+      "block_sparse_moe.experts.3.w2",
+      "block_sparse_moe.experts.4.w2",
+      "block_sparse_moe.experts.5.w2",
+      "block_sparse_moe.experts.6.w2",
+      "block_sparse_moe.experts.7.w2"
+    ]
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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>",
+  "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 %}",
+  "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
+}