GPTQ model commit

LICENSE

@@ -0,0 +1,48 @@
+DEEPNIGHT_RESPONSIBLE_AI LICENSE
+
+This DEEPNIGHT_RESPONSIBLE_AI License (the "License") is a legal agreement between you (the "Licensee") and DEEPNIGHT,
+governing the use of the artificial intelligence models (the "Models") provided by DEEPNIGHT.
+
+1. Grant of License
+Subject to the terms and conditions of this License, DEEPNIGHT grants Licensee a personal,
+non-exclusive, non-transferable license to use the Models for personal, non-commercial purposes only.
+
+2. Restrictions
+Licensee shall not use the Models for any commercial purposes,
+including but not limited to the development of products or services for sale,
+without the express written consent of DEEPNIGHT.
+
+3. Responsible Use
+The Models are provided uncensored, and Licensee agrees to use them responsibly and in compliance with
+all applicable laws and regulations. 
+DEEPNIGHT disclaims any responsibility for the misuse of the Models, and Licensee acknowledges that they
+are solely responsible for their use.
+
+4. No Warranty
+The Models are provided "as is" without any warranty of any kind, either express or implied,
+including but not limited to the implied warranties of merchantability and fitness for a particular purpose.
+DEEPNIGHT makes no representations or warranties regarding the accuracy or completeness of the Models.
+
+5. Limitation of Liability
+In no event shall DEEPNIGHT be liable for any special, incidental, indirect, or consequential
+damages of any kind arising out of or in connection with the use or performance of the Models.
+
+6. Termination
+This License is effective until terminated. DEEPNIGHT reserves the right to
+terminate this License at any time if Licensee fails to comply with its terms.
+
+7. Governing Law
+This License shall be governed by and construed in accordance with the laws of the jurisdiction in which
+the Licensee is located, without regard to its conflict of law principles.
+
+This modification allows the License to be governed by the laws of the jurisdiction where the
+Licensee is located, providing a more global coverage. Make sure that this aligns with your intended
+usage and consult with legal professionals to ensure its suitability for your specific circumstances.
+
+8. Miscellaneous
+Any modifications or amendments to this License must be made in writing and signed by both parties.
+If any provision of this License is held to be unenforceable,
+the remaining provisions shall remain in full force and effect.
+
+
+By using the Model, Licensee agrees to be bound by the terms and conditions of this DEEPNIGHT_RESPONSIBLE_AI License.

config.json

@@ -0,0 +1,68 @@
+{
+    "_name_or_path": "/workspace/process/deepnight-research_saily_220b/source",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 243,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 4,
+        "block_name_to_quantize": null,
+        "cache_block_outputs": true,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "exllama_config": {
+            "version": 1
+        },
+        "group_size": -1,
+        "max_input_length": null,
+        "model_seqlen": null,
+        "module_name_preceding_first_block": null,
+        "modules_in_block_to_quantize": [
+            [
+                "self_attn.k_proj",
+                "self_attn.v_proj",
+                "self_attn.q_proj"
+            ],
+            [
+                "self_attn.o_proj"
+            ],
+            [
+                "mlp.up_proj",
+                "mlp.gate_proj"
+            ],
+            [
+                "mlp.down_proj"
+            ]
+        ],
+        "pad_token_id": null,
+        "quant_method": "gptq",
+        "sym": true,
+        "tokenizer": null,
+        "true_sequential": true,
+        "use_cuda_fp16": false,
+        "use_exllama": true
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.37.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb189c1059b67689879b19ce9f13af5c5807cc797d1a5bf76fe5b740faa4741d
+size 48987746256

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3e283b6eeea48fd3b15e5a34dcfb349057907c4949aa0c166a321d1f964942
+size 48892007440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c3ab324d2e60543b4c38411fc0a67716ad28fd06c3586b538462900c03ad4d
+size 7305312592

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 4,
+    "group_size": -1,
+    "damp_percent": 0.1,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}