Upload model checkpoints directly from S3

config.json

@@ -0,0 +1,33 @@
+{
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 32013,
+ "eos_token_id": 32021,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 2048,
+ "initializer_range": 0.02,
+ "intermediate_size": 5504,
+ "max_position_embeddings": 16384,
+ "mlp_bias": false,
+ "model_type": "llama",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "num_key_value_heads": 16,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": {
+ "factor": 4.0,
+ "rope_type": "linear",
+ "type": "linear"
+ },
+ "rope_theta": 100000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.43.4",
+ "use_cache": false,
+ "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 32013,
+ "eos_token_id": 32021,
+ "transformers_version": "4.43.4",
+ "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74b31c685d90f24bd24078c2998ddfdbf2494cca9a3fccd783db01b6ac017b5
+size 2692969128

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af36d76e229dffd01151b1282f750941526122c69a82006f87af3892ed10f31
+size 2693014838

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "32000": {
+ "content": "õ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32001": {
+ "content": "÷",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32002": {
+ "content": "Á",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32003": {
+ "content": "ý",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32004": {
+ "content": "À",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32005": {
+ "content": "ÿ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32006": {
+ "content": "ø",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32007": {
+ "content": "ú",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32008": {
+ "content": "þ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32009": {
+ "content": "ü",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32010": {
+ "content": "ù",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32011": {
+ "content": "ö",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32012": {
+ "content": "û",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32013": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32014": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32015": {
+ "content": "<｜fim▁hole｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32016": {
+ "content": "<｜fim▁begin｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32017": {
+ "content": "<｜fim▁end｜>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32018": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32019": {
+ "content": "<|User|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32020": {
+ "content": "<|Assistant|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "32021": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|EOT|>",
+ "legacy": true,
+ "model_max_length": 4096,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}