Upload folder using huggingface_hub

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "fxmarty/small-llama-testing",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "algo_config": {
+      "model_decoder_layers": "model.layers",
+      "name": "awq",
+      "processor": "AwqProcessor",
+      "scaling_layers": [
+        {
+          "inp": "self_attn.q_proj",
+          "layers": [
+            "self_attn.q_proj",
+            "self_attn.k_proj",
+            "self_attn.v_proj"
+          ],
+          "module2inspect": "self_attn",
+          "prev_op": "input_layernorm"
+        },
+        {
+          "condition": "module.self_attn.v_proj.weight.shape == module.self_attn.o_proj.weight.shape",
+          "help": "attention out, Please refer to https://github.com/mit-han-lab/llm-awq/pull/67#issue-1850622696, if module.self_attn.v_proj.weight.shape == module.self_attn.o_proj.weight.shape",
+          "inp": "self_attn.o_proj",
+          "layers": [
+            "self_attn.o_proj"
+          ],
+          "prev_op": "self_attn.v_proj"
+        },
+        {
+          "inp": "mlp.gate_proj",
+          "layers": [
+            "mlp.gate_proj",
+            "mlp.up_proj"
+          ],
+          "module2inspect": "mlp",
+          "prev_op": "post_attention_layernorm"
+        },
+        {
+          "inp": "mlp.down_proj",
+          "layers": [
+            "mlp.down_proj"
+          ],
+          "prev_op": "mlp.up_proj"
+        }
+      ]
+    },
+    "exclude": [
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": null,
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": 1,
+        "dtype": "int4",
+        "group_size": 4,
+        "is_dynamic": false,
+        "observer_cls": "PerGroupMinMaxObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_type": "float",
+        "symmetric": true
+      }
+    },
+    "layer_quant_config": {},
+    "layer_type_quant_config": {},
+    "pack_method": "reorder",
+    "quant_method": "quark",
+    "quant_mode": "eager_mode"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2182117bee4dc6baf6173af5c0ca550171df3bc4096aa5386478ab05f2b28aa0
+size 66718056

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 512,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}