Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+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 [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) but with smaller size. 
+
+Codes:
+```python
+from transformers import pipeline
+from huggingface_hub import create_repo, upload_folder
+import torch
+import transformers
+import os
+
+model_id = 'mistralai/Mistral-Nemo-Instruct-2407'
+repo_id = 'yujiepan/mistral-nemo-2407-tiny-random'
+save_path = f'/tmp/{repo_id}'
+
+config = transformers.AutoConfig.from_pretrained(model_id)
+config.hidden_size = 8
+config.intermediate_size = 32
+config.num_attention_heads = 4
+config.num_hidden_layers = 2
+config.num_key_value_heads = 2
+config.head_dim = 2
+print(config)
+
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
+tokenizer.save_pretrained(save_path)
+
+model = transformers.AutoModelForCausalLM.from_config(config, torch_dtype=torch.bfloat16)
+model.generation_config = transformers.GenerationConfig.from_pretrained(model_id)
+
+transformers.set_seed(42)
+with torch.no_grad():
+    for _, p in sorted(model.named_parameters()):
+        torch.nn.init.uniform_(p, -0.1, 0.1)
+
+pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, do_sample=False, device='cuda')
+print(pipe('Hello World!'))
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+chatbot = pipeline("text-generation", model=save_path, max_length=1000, max_new_tokens=16)
+print(chatbot(messages))
+
+model.save_pretrained(save_path)
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62ca92cd05e9be1e4622b8a686c078cdb83e213eb164f95509fa528ca8aa637
+size 4200408

special_tokens_map.json

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