Upload folder using huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+license: apache-2.0
+---
+
+# CorticalStack/mistral-7b-openhermes-gptq
+
+CorticalStack/mistral-7b-openhermes-gptq is an GPTQ quantised version of [CorticalStack/mistral-7b-openhermes-sft](https://huggingface.co/CorticalStack/mistral-7b-openhermes-sft).
+
+GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). MacOS users: please use GGUF models.
+
+These GPTQ models are known to work in the following inference servers/webuis.
+- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
+- [KoboldAI United](https://github.com/henk717/koboldai)
+- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "mistral-7b-openhermes-sft",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "dataset": "wikitext2",
+    "desc_act": false,
+    "group_size": 128,
+    "modules_in_block_to_quantize": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "unsloth_version": "2024.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a9d1433087defb32300dcce7305ad534c0a8fcfbebf4c3c72b9f6874b33b53
+size 4158662096

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "dataset": "wikitext2",
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "quant_method": "gptq",
+  "modules_in_block_to_quantize": null
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}