projecte-aina/aguila-7b: 8bits, gr128, desc_act=False

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "projecte-aina/aguila-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "projecte-aina/aguila-7b--configuration_RW.RWConfig",
+    "AutoModel": "projecte-aina/aguila-7b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "projecte-aina/aguila-7b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "projecte-aina/aguila-7b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "projecte-aina/aguila-7b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "projecte-aina/aguila-7b--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "pad_token_id": 50256,
+  "parallel_attn": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

gptq_model-8bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd2b3ffd9ce265be62084ba3995b5e180785b078ccd9a8b02df16ce9e03d931
+size 7702832848

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 8,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "aguila-7b-8bit",
+  "model_file_base_name": "gptq_model-8bit-128g"
+}