Upload folder using huggingface_hub

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+inference: true
+widget:
+- text: Hello!
+  example_title: Hello world
+  group: Python
+---
+
+This model is for debugging. It is randomly initialized using the config from [microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) but with smaller size. 
+
+Codes:
+```python
+import os
+
+import torch
+import transformers
+from transformers import (AutoConfig, AutoModelForCausalLM, AutoTokenizer,
+                          GenerationConfig, pipeline, set_seed)
+
+model_id = "microsoft/Phi-3.5-MoE-instruct"
+repo_id = "yujiepan/phi-3.5-moe-tiny-random"
+save_path = f"/tmp/{repo_id}"
+
+config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
+config.hidden_size = 16
+config.intermediate_size = 32
+config.num_attention_heads = 4
+config.num_hidden_layers = 2
+config.num_key_value_heads = 4
+config.rope_scaling['long_factor'] = [1.0299, 1.0499]
+config.rope_scaling['short_factor'] = [1.05, 1.05]
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+tokenizer.save_pretrained(save_path)
+
+model = AutoModelForCausalLM.from_config(
+    config, torch_dtype=torch.bfloat16,
+    # attn_implementation="sdpa",
+    trust_remote_code=True,
+)
+model.generation_config = GenerationConfig.from_pretrained(
+    model_id, trust_remote_code=True
+)
+
+set_seed(42)
+with torch.no_grad():
+    for _, p in sorted(model.named_parameters()):
+        torch.nn.init.uniform_(p, -0.3, 0.3)
+
+model.save_pretrained(save_path)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device="cuda",
+                trust_remote_code=True, max_new_tokens=20)
+print(pipe('Hello'))
+```

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "microsoft/Phi-3.5-MoE-instruct",
+  "architectures": [
+    "PhiMoEForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3.5-MoE-instruct--configuration_phimoe.PhiMoEConfig",
+    "AutoModelForCausalLM": "microsoft/Phi-3.5-MoE-instruct--modeling_phimoe.PhiMoEForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "input_jitter_noise": 0.01,
+  "intermediate_size": 32,
+  "lm_head_bias": true,
+  "max_position_embeddings": 131072,
+  "model_type": "phimoe",
+  "num_attention_heads": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "num_local_experts": 16,
+  "original_max_position_embeddings": 4096,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0299,
+      1.0499
+    ],
+    "long_mscale": 1.243163121016122,
+    "original_max_position_embeddings": 4096,
+    "short_factor": [
+      1.05,
+      1.05
+    ],
+    "short_mscale": 1.243163121016122,
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.0,
+  "router_jitter_noise": 0.01,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274d3c66b5dde81a176acc899de3ec6a63e93d14b1c4c5bd8ff9f694c1a4d9f3
+size 2234992

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}