Upload LlamaForCausalLM

config.json

@@ -1,84 +1,84 @@
 {
-    "vocab_size": 32000,
-    "max_position_embeddings": 2048,
-    "hidden_size": 2048,
-    "intermediate_size": 5632,
-    "num_hidden_layers": 22,
-    "num_attention_heads": 32,
-    "num_key_value_heads": 4,
-    "hidden_act": "silu",
-    "initializer_range": 0.02,
-    "rms_norm_eps": 1e-05,
-    "pretraining_tp": 1,
-    "use_cache": true,
-    "rope_theta": 10000.0,
-    "rope_scaling": null,
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "torch_dtype": "float16",
-    "tie_word_embeddings": false,
-    "architectures": [
-        "LlamaForCausalLM"
+  "_name_or_path": "/nfs/scistore14/alistgrp/apanfero/models/TinyLlama-1.1B-Chat-v1_0-AQLM-2Bit-1x16-hf/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "in_group_size": 8,
+    "linear_weights_not_to_quantize": [
+      "model.layers.0.input_layernorm.weight",
+      "model.layers.0.post_attention_layernorm.weight",
+      "model.layers.1.input_layernorm.weight",
+      "model.layers.1.post_attention_layernorm.weight",
+      "model.layers.2.input_layernorm.weight",
+      "model.layers.2.post_attention_layernorm.weight",
+      "model.layers.3.input_layernorm.weight",
+      "model.layers.3.post_attention_layernorm.weight",
+      "model.layers.4.input_layernorm.weight",
+      "model.layers.4.post_attention_layernorm.weight",
+      "model.layers.5.input_layernorm.weight",
+      "model.layers.5.post_attention_layernorm.weight",
+      "model.layers.6.input_layernorm.weight",
+      "model.layers.6.post_attention_layernorm.weight",
+      "model.layers.7.input_layernorm.weight",
+      "model.layers.7.post_attention_layernorm.weight",
+      "model.layers.8.input_layernorm.weight",
+      "model.layers.8.post_attention_layernorm.weight",
+      "model.layers.9.input_layernorm.weight",
+      "model.layers.9.post_attention_layernorm.weight",
+      "model.layers.10.input_layernorm.weight",
+      "model.layers.10.post_attention_layernorm.weight",
+      "model.layers.11.input_layernorm.weight",
+      "model.layers.11.post_attention_layernorm.weight",
+      "model.layers.12.input_layernorm.weight",
+      "model.layers.12.post_attention_layernorm.weight",
+      "model.layers.13.input_layernorm.weight",
+      "model.layers.13.post_attention_layernorm.weight",
+      "model.layers.14.input_layernorm.weight",
+      "model.layers.14.post_attention_layernorm.weight",
+      "model.layers.15.input_layernorm.weight",
+      "model.layers.15.post_attention_layernorm.weight",
+      "model.layers.16.input_layernorm.weight",
+      "model.layers.16.post_attention_layernorm.weight",
+      "model.layers.17.input_layernorm.weight",
+      "model.layers.17.post_attention_layernorm.weight",
+      "model.layers.18.input_layernorm.weight",
+      "model.layers.18.post_attention_layernorm.weight",
+      "model.layers.19.input_layernorm.weight",
+      "model.layers.19.post_attention_layernorm.weight",
+      "model.layers.20.input_layernorm.weight",
+      "model.layers.20.post_attention_layernorm.weight",
+      "model.layers.21.input_layernorm.weight",
+      "model.layers.21.post_attention_layernorm.weight",
+      "model.embed_tokens.weight",
+      "model.norm.weight",
+      "lm_head.weight"
     ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-    "transformers_version": "4.38.0.dev0",
-    "model_type": "llama",
-    "quantization_config": {
-        "quant_method": "aqlm",
-        "nbits_per_codebook": 16,
-        "num_codebooks": 1,
-        "out_group_size": 1,
-        "in_group_size": 8,
-        "linear_weights_not_to_quantize": [
-            "model.layers.0.input_layernorm.weight",
-            "model.layers.0.post_attention_layernorm.weight",
-            "model.layers.1.input_layernorm.weight",
-            "model.layers.1.post_attention_layernorm.weight",
-            "model.layers.2.input_layernorm.weight",
-            "model.layers.2.post_attention_layernorm.weight",
-            "model.layers.3.input_layernorm.weight",
-            "model.layers.3.post_attention_layernorm.weight",
-            "model.layers.4.input_layernorm.weight",
-            "model.layers.4.post_attention_layernorm.weight",
-            "model.layers.5.input_layernorm.weight",
-            "model.layers.5.post_attention_layernorm.weight",
-            "model.layers.6.input_layernorm.weight",
-            "model.layers.6.post_attention_layernorm.weight",
-            "model.layers.7.input_layernorm.weight",
-            "model.layers.7.post_attention_layernorm.weight",
-            "model.layers.8.input_layernorm.weight",
-            "model.layers.8.post_attention_layernorm.weight",
-            "model.layers.9.input_layernorm.weight",
-            "model.layers.9.post_attention_layernorm.weight",
-            "model.layers.10.input_layernorm.weight",
-            "model.layers.10.post_attention_layernorm.weight",
-            "model.layers.11.input_layernorm.weight",
-            "model.layers.11.post_attention_layernorm.weight",
-            "model.layers.12.input_layernorm.weight",
-            "model.layers.12.post_attention_layernorm.weight",
-            "model.layers.13.input_layernorm.weight",
-            "model.layers.13.post_attention_layernorm.weight",
-            "model.layers.14.input_layernorm.weight",
-            "model.layers.14.post_attention_layernorm.weight",
-            "model.layers.15.input_layernorm.weight",
-            "model.layers.15.post_attention_layernorm.weight",
-            "model.layers.16.input_layernorm.weight",
-            "model.layers.16.post_attention_layernorm.weight",
-            "model.layers.17.input_layernorm.weight",
-            "model.layers.17.post_attention_layernorm.weight",
-            "model.layers.18.input_layernorm.weight",
-            "model.layers.18.post_attention_layernorm.weight",
-            "model.layers.19.input_layernorm.weight",
-            "model.layers.19.post_attention_layernorm.weight",
-            "model.layers.20.input_layernorm.weight",
-            "model.layers.20.post_attention_layernorm.weight",
-            "model.layers.21.input_layernorm.weight",
-            "model.layers.21.post_attention_layernorm.weight",
-            "model.embed_tokens.weight",
-            "model.norm.weight",
-            "lm_head.weight"
-        ]
-    }
-}
+    "nbits_per_codebook": 16,
+    "num_codebooks": 1,
+    "out_group_size": 1,
+    "quant_method": "aqlm"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0.dev0",
+  "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": "4.38.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc4d941e02caa14f725916f97f925703efbedf260189c2cbad022c18e237b6a
+size 666876880