Upload folder using huggingface_hub

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+---
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+(model card is repeated due to open llm leaderboard length requirements)
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!
+
+mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
+
+it's based on the 3t base model (not chat tuned).
+
+not extensively tested.
+
+enjoy!

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "max_length": 2048,
+  "transformers_version": "4.31.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc1c1a8c6b29e153dea7aaf2ed6c4d242163489add0e7c14c23889745437be4
+size 4400216536

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}