diff --git a/.cache/huggingface/download/README.md.lock b/.cache/huggingface/download/README.md.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/README.md.metadata b/.cache/huggingface/download/README.md.metadata new file mode 100644 index 0000000..c7e9655 --- /dev/null +++ b/.cache/huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +8abaf05e0c557741647b35a61be804104fcca542 +1737565686.7738845 diff --git a/.cache/huggingface/download/config.json.lock b/.cache/huggingface/download/config.json.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/config.json.metadata b/.cache/huggingface/download/config.json.metadata new file mode 100644 index 0000000..424c925 --- /dev/null +++ b/.cache/huggingface/download/config.json.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +2df560ba238f82db11cd683c2d31d46cf4576658 +1737565686.5782778 diff --git a/.cache/huggingface/download/generation_config.json.lock b/.cache/huggingface/download/generation_config.json.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/generation_config.json.metadata b/.cache/huggingface/download/generation_config.json.metadata new file mode 100644 index 0000000..4ecb806 --- /dev/null +++ b/.cache/huggingface/download/generation_config.json.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +83b77ea2d7f5e38edb3fa9ceed9a84530bd26593 +1737565686.7369707 diff --git a/.cache/huggingface/download/model.safetensors.lock b/.cache/huggingface/download/model.safetensors.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/model.safetensors.metadata b/.cache/huggingface/download/model.safetensors.metadata new file mode 100644 index 0000000..8cc7c2a --- /dev/null +++ b/.cache/huggingface/download/model.safetensors.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +68a2e4be76fa709455a60272fba8e512c02d81c46e6c671cc9449e374fd6809a +1737565745.4815474 diff --git a/.cache/huggingface/download/special_tokens_map.json.lock b/.cache/huggingface/download/special_tokens_map.json.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/special_tokens_map.json.metadata b/.cache/huggingface/download/special_tokens_map.json.metadata new file mode 100644 index 0000000..36a1e29 --- /dev/null +++ b/.cache/huggingface/download/special_tokens_map.json.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +68b10c7f0a479eae0c358eac6a14959b3f9acdf1 +1737565686.7442381 diff --git a/.cache/huggingface/download/tokenizer.json.lock b/.cache/huggingface/download/tokenizer.json.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/tokenizer.json.metadata b/.cache/huggingface/download/tokenizer.json.metadata new file mode 100644 index 0000000..0728f4a --- /dev/null +++ b/.cache/huggingface/download/tokenizer.json.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +1737565687.5542464 diff --git a/.cache/huggingface/download/tokenizer_config.json.lock b/.cache/huggingface/download/tokenizer_config.json.lock new file mode 100644 index 0000000..e69de29 diff --git a/.cache/huggingface/download/tokenizer_config.json.metadata b/.cache/huggingface/download/tokenizer_config.json.metadata new file mode 100644 index 0000000..b1ec1a2 --- /dev/null +++ b/.cache/huggingface/download/tokenizer_config.json.metadata @@ -0,0 +1,3 @@ +8330ca72fe8cf1fc86a8b20b4835dc08fbbd2251 +0269fe29612662f1015a99e0ba5414813d710cba +1737565686.587959 diff --git a/.gitattributes b/.gitattributes index 52373fe..602d20f 100644 --- a/.gitattributes +++ b/.gitattributes @@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/config.json b/config.json index 9fd4569..2df560b 100644 --- a/config.json +++ b/config.json @@ -18,6 +18,7 @@ "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, + "pad_token_id": 128004, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { @@ -30,7 +31,8 @@ "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", - "transformers_version": "4.44.2", + "transformers_version": "4.48.1", + "unsloth_fixed": true, "use_cache": true, "vocab_size": 128256 } diff --git a/generation_config.json b/generation_config.json index a4ca98e..83b77ea 100644 --- a/generation_config.json +++ b/generation_config.json @@ -1,6 +1,11 @@ { "_from_model_config": true, "bos_token_id": 128000, + "do_sample": true, "eos_token_id": 128001, - "transformers_version": "4.44.2" + "max_length": 131072, + "pad_token_id": 128004, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.48.1" } diff --git a/tokenizer.json b/tokenizer.json index 66cd9d7..1c1d8d5 100644 --- a/tokenizer.json +++ b/tokenizer.json @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 -size 9085657 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json index fcacf1b..0269fe2 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -1,4 +1,5 @@ { + "add_bos_token": true, "added_tokens_decoder": { "128000": { "content": "<|begin_of_text|>", @@ -2052,6 +2053,7 @@ "bos_token": "<|begin_of_text|>", "clean_up_tokenization_spaces": true, "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, "model_input_names": [ "input_ids", "attention_mask" @@ -2059,5 +2061,6 @@ "model_max_length": 131072, "pad_token": "<|finetune_right_pad_id|>", "padding_side": "left", - "tokenizer_class": "PreTrainedTokenizerFast" + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": null }