Upload folder using huggingface_hub

config.json

@@ -0,0 +1,304 @@
+{
+  "_name_or_path": "microsoft/Phi-3-small-128k-instruct",
+  "architectures": [
+    "Phi3SmallForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-small-128k-instruct--configuration_phi3_small.Phi3SmallConfig",
+    "AutoModelForCausalLM": "microsoft/Phi-3-small-128k-instruct--modeling_phi3_small.Phi3SmallForCausalLM",
+    "AutoTokenizer": "microsoft/Phi-3-small-128k-instruct--tokenization_phi3_small.Phi3SmallTokenizer"
+  },
+  "blocksparse_block_size": 64,
+  "blocksparse_homo_head_pattern": false,
+  "blocksparse_num_local_blocks": 16,
+  "blocksparse_triton_kernel_block_size": 64,
+  "blocksparse_vert_stride": 8,
+  "bos_token_id": 100257,
+  "dense_attention_every_n_layers": 2,
+  "dummy_token_indices": [
+    100256,
+    100258,
+    100259,
+    100260,
+    100264,
+    100265,
+    100267,
+    100268,
+    100269,
+    100270,
+    100271,
+    100272,
+    100273,
+    100274,
+    100275,
+    100276,
+    100277,
+    100278,
+    100279,
+    100280,
+    100281,
+    100282,
+    100283,
+    100284,
+    100285,
+    100286,
+    100287,
+    100288,
+    100289,
+    100290,
+    100291,
+    100292,
+    100293,
+    100294,
+    100295,
+    100296,
+    100297,
+    100298,
+    100299,
+    100300,
+    100301,
+    100302,
+    100303,
+    100304,
+    100305,
+    100306,
+    100307,
+    100308,
+    100309,
+    100310,
+    100311,
+    100312,
+    100313,
+    100314,
+    100315,
+    100316,
+    100317,
+    100318,
+    100319,
+    100320,
+    100321,
+    100322,
+    100323,
+    100324,
+    100325,
+    100326,
+    100327,
+    100328,
+    100329,
+    100330,
+    100331,
+    100332,
+    100333,
+    100334,
+    100335,
+    100336,
+    100337,
+    100338,
+    100339,
+    100340,
+    100341,
+    100342,
+    100343,
+    100344,
+    100345,
+    100346,
+    100347,
+    100348,
+    100349,
+    100350,
+    100351
+  ],
+  "embedding_dropout_prob": 0.1,
+  "eos_token_id": 100257,
+  "ff_dim_multiplier": null,
+  "ff_intermediate_size": 14336,
+  "ffn_dropout_prob": 0.1,
+  "gegelu_limit": 20.0,
+  "gegelu_pad_to_256": true,
+  "hidden_act": "gegelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3small",
+  "mup_attn_multiplier": 1.0,
+  "mup_embedding_multiplier": 10.0,
+  "mup_use_scaling": true,
+  "mup_width_multiplier": 8.0,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 8192,
+  "pad_sequence_to_multiple_of_64": true,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+  "reorder_and_upcast_attn": false,
+  "rope_embedding_base": 1000000,
+  "rope_position_scale": 1.0,
+  "rope_scaling": {
+    "long_factor": [
+      1.0,
+      1.01,
+      1.01,
+      1.02,
+      1.04,
+      1.04,
+      1.04,
+      1.05,
+      1.05,
+      1.06,
+      1.07,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.09,
+      1.09,
+      1.2,
+      2.31,
+      3.76,
+      9.38,
+      10.1,
+      10.8,
+      18.1,
+      25.2,
+      25.3,
+      26.1,
+      26.6,
+      30.2,
+      33.0,
+      41.5,
+      44.4,
+      44.8,
+      50.2,
+      51.9,
+      59.3,
+      62.7,
+      66.1,
+      66.3,
+      85.8,
+      89.3,
+      90.0,
+      99.9,
+      107.0,
+      110.0,
+      111.0,
+      117.0,
+      118.0,
+      121.0,
+      122.0,
+      127.0,
+      127.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      128.0,
+      129.0,
+      129.0,
+      129.0
+    ],
+    "long_mscale": 1.1902380714238083,
+    "original_max_position_embeddings": 8192,
+    "short_factor": [
+      1.02,
+      1.02,
+      1.05,
+      1.05,
+      1.06,
+      1.08,
+      1.08,
+      1.08,
+      1.08,
+      1.12,
+      1.1800000000000002,
+      1.1900000000000002,
+      1.1900000000000002,
+      1.2100000000000002,
+      1.2300000000000002,
+      1.2400000000000002,
+      1.2400000000000002,
+      1.2500000000000002,
+      1.3000000000000003,
+      1.3100000000000003,
+      1.4600000000000004,
+      1.5100000000000005,
+      1.7000000000000006,
+      1.9300000000000008,
+      2.080000000000001,
+      2.4399999999999933,
+      3.2199999999999767,
+      3.4499999999999718,
+      3.579999999999969,
+      4.669999999999946,
+      4.779999999999943,
+      5.999999999999917,
+      6.009999999999917,
+      6.4199999999999084,
+      6.619999999999904,
+      7.189999999999892,
+      7.3099999999998895,
+      7.339999999999889,
+      7.479999999999886,
+      9.749999999999837,
+      10.919999999999812,
+      11.219999999999805,
+      11.749999999999794,
+      11.979999999999789,
+      13.239999999999762,
+      13.579999999999755,
+      13.669999999999753,
+      13.82999999999975,
+      14.009999999999746,
+      14.679999999999731,
+      14.889999999999727,
+      15.769999999999708,
+      15.769999999999708,
+      15.819999999999707,
+      15.839999999999707,
+      15.919999999999705,
+      16.029999999999703,
+      16.12999999999972,
+      16.44999999999977,
+      16.44999999999977,
+      16.77999999999982,
+      16.83999999999983,
+      16.83999999999983,
+      16.889999999999837
+    ],
+    "short_mscale": 1.0,
+    "type": "su"
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": [
+    100257,
+    100266
+  ],
+  "transformers_version": "4.43.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8949e40abcea32801640b0abcf6addb74ee6353980106675673868fdc80f7c2d
+size 4455372080

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "_commit_hash": "f80aaa30bfc64c2b8ab214b541d9050e97163bc4",
+  "_from_auto": true,
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_phi3_small.Phi3SmallTokenizer",
+      "tokenization_phi3_small.Phi3SmallTokenizer"
+    ]
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "Phi3SmallTokenizer",
+  "trust_remote_code": true
+}