Upload folder using huggingface_hub

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "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,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.005,
+    "desc_act": true,
+    "group_size": 32,
+    "lm_head": false,
+    "meta": {
+      "quantizer": "gptqmodel:0.9.9"
+    },
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "vocab_size": 32032
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edaa9f2a2998403349da6e5c6b5cc97847e635cdc2d0984243d1c52fd6d06bbf
+size 4565354704

quantize_config.json

@@ -0,0 +1,17 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "lm_head": false,
+  "damp_percent": 0.005,
+  "true_sequential": true,
+  "model_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B-4bit-32g",
+  "model_file_base_name": "model",
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "meta": {
+    "quantizer": "gptqmodel:0.9.9"
+  }
+}