Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Xenova/llama2.c-stories15M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 288,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "max_position_embeddings": 256,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 6,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "1.6.0.20231111",
+  "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": "1.6.0.20231111"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b444d2abc30a7a6c6ea0dc45bc3adcea1679c02593527945dba4e8c24f9f783b
+size 61107230

recipe.yaml

@@ -0,0 +1,31 @@
+test_stage:
+  obcq_modifiers:
+    SmoothQuantModifier:
+      smoothing_strength: 0.8
+      mappings: [
+        [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
+        [["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"]
+      ]
+    QuantizationModifier:
+      ignore:
+        - LlamaRotaryEmbedding
+        - LlamaRMSNorm
+        - SiLUActivation
+      post_oneshot_calibration: True
+      scheme_overrides:
+        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
+    #   mask_structure: "0:0"
+    #   targets: [
+    #     "re:model.layers.\\d*$"
+    #   ]
+    #   target_ids: ["attention_mask", "position_ids"]  

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}