Upload model files and evals

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/shubhra/neuralmagic/Llama-2-7b-cnn-daily-mail-pruned_70/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "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": "4.39.3"
+}

model-orig.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da7d0f19c8ccbe92f9db7f251f2b20cd36291b0931a2506c125a3de67d9f827
+size 1222401

model.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456b03ae91cf4d2fb766adb6549fea01238174b137fc12e88840134d01edeebd
+size 7154772992

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03f68324b501c507ed785141bee85bb63121dcee750dd96b79b4cdd8c204052
+size 1207346

recipe.yaml

@@ -0,0 +1,39 @@
+test_stage:
+  obcq_modifiers:
+    SmoothQuantModifier:
+      smoothing_strength: 0.9
+      mappings:
+      - - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
+        - re:.*input_layernorm
+      - - ['re:.*gate_proj', 're:.*up_proj']
+        - re:.*post_attention_layernorm
+      - - ['re:.*down_proj']
+        - re:.*up_proj
+    QuantizationModifier:
+      ignore: [LlamaRotaryEmbedding, LlamaRMSNorm, SiLUActivation, model.layers.1.mlp.down_proj,
+        model.layers.30.mlp.down_proj, model.layers.0.mlp.down_proj]
+      post_oneshot_calibration: true
+      scheme_overrides:
+        Linear:
+          weights: {num_bits: 8, symmetric: true, strategy: channel}
+        MatMulLeftInput_QK:
+          input_activation: {num_bits: 8, symmetric: true}
+        Embedding:
+          input_activations: null
+          weights: {num_bits: 8, symmetric: false}
+    SparseGPTModifier:
+      sparsity: 0.0
+      block_size: 128
+      sequential_update: false
+      quantize: true
+      percdamp: 0.01
+      prunen: 0
+      prunem: 0
+      targets: [model.layers.0, model.layers.1, model.layers.2, model.layers.3, model.layers.4,
+        model.layers.5, model.layers.6, model.layers.7, model.layers.8, model.layers.9, model.layers.10,
+        model.layers.11, model.layers.12, model.layers.13, model.layers.14, model.layers.15,
+        model.layers.16, model.layers.17, model.layers.18, model.layers.19, model.layers.20,
+        model.layers.21, model.layers.22, model.layers.23, model.layers.24, model.layers.25,
+        model.layers.26, model.layers.27, model.layers.28, model.layers.29, model.layers.30,
+        model.layers.31, lm_head]
+      target_ids: [attention_mask, position_ids]

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}