Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

config.json +38 -0
generation_config.json +8 -0
merges.txt +0 -0
model.safetensors +3 -0
special_tokens_map.json +34 -0
tokenizer.json +0 -0
tokenizer_config.json +154 -0
vocab.json +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+ "_name_or_path": "/root/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-1.7B-Instruct/snapshots/df32c35db9f85f9c44997dcf694d1a79e944ff69",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 2048,
+ "initializer_range": 0.02,
+ "intermediate_size": 8192,
+ "max_position_embeddings": 2048,
+ "mlp_bias": false,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 32,
+ "pad_token_id": 2,
+ "pretraining_tp": 1,
+ "quantization_config": {
+ "bits": 4,
+ "group_size": 128,
+ "modules_to_not_convert": null,
+ "quant_method": "awq",
+ "version": "gemm",
+ "zero_point": true
+ },
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
+ "tie_word_embeddings": true,
+ "torch_dtype": "float16",
+ "transformers_version": "4.43.2",
+ "use_cache": true,
+ "vocab_size": 49152
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "do_sample": true,
+ "eos_token_id": 2,
+ "pad_token_id": 2,
+ "transformers_version": "4.43.2"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dbc8e4110ba59b3f73b5d8efd1c3865eb89dabcd90503a994f4e9c15c7b074
+size 1239679848

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,34 @@

+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,154 @@

+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<repo_name>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<reponame>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<file_sep>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<filename>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<gh_stars>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": "<issue_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": "<issue_comment>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": "<issue_closed>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<jupyter_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "12": {
+ "content": "<jupyter_text>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "13": {
+ "content": "<jupyter_code>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "14": {
+ "content": "<jupyter_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "15": {
+ "content": "<jupyter_script>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "16": {
+ "content": "<empty_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": "<|im_start|>",
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "model_max_length": 2048,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>",
+ "vocab_size": 49152
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff