Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,11 @@ 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,40 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "BitAgent/BitAgent-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.46.3"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2820c2e0d37a1cc328b565dad0d4dd046014ad019a9ab36d4a42076b9d99178c
+size 858913

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cb98920e139831a59b646cb94c23aab1cb196fba23d6bd92df1833fdba04eb
+size 32121044992

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc801c8dfe29969b2eec41d0573b29379216eaacece6c70dc41d77313da1b8d3
+size 911812

onnx/model_bnb4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3fbe321a23cc317f4aee814cffb0e06da22ef67beecc348ac9563a0b2b46ee
+size 6323781632

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e433067465035737ea41e5ac77f57d78e1c13a9f56a608d5128dba1c96c86729
+size 860108

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46127b1031f7f0b00e52dddbe1e5dbfd6951aa3f02cd958368eb4c8f2b72d6dc
+size 16060522496

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18320ada4cd328d3fc961208630f1a8182870decdb2827ce44ea7f3409e101e2
+size 1105763

onnx/model_int8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfe2e505261c7525cb64ec9ef4e89186615827976bf75353feb68aeb4d67a58
+size 8031059968

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b227ea755687c25f4d05e419995cf4086b7e0bbda5fbef9cf6266e36e966e7
+size 908949

onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae33d35e5440dfebf8200dc67dbd1004f23c74f50033e78bfa55613f7a6b1a6f
+size 6792822784

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db288a7c3680f9e017e993287e81743f1d6c6924c79c391d3639cb6a042fbd83
+size 910416

onnx/model_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43c328aec0d413d274daa95c2ac2224fe5932100e3e3a6199a339b88e03ac4a
+size 5272576000

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2ab43099c7f50de8e7aeb4d02bf070d5e8edcfe0b0866dd477eb0bbd36aa92
+size 1107250

onnx/model_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfe2e505261c7525cb64ec9ef4e89186615827976bf75353feb68aeb4d67a58
+size 8031059968

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66871a7553e6124221d59f4899b894ed8ce388157f3c11a636c5fa598285283
+size 1106175

onnx/model_uint8.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d83ee32f8088c76e501d9e092eb9e452108eb5c999ba01f7f554e445186be7
+size 8031059968

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": false,
+    "reduce_range": false,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|finetune_right_pad_id|>"
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f4a1a7159f2dacfa01410288c1b9faee8d5e309c880cb3dfc8e9ab3e070cef
-size 17209915
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -9,7 +9,7 @@
       "special": true
     },
     "128001": {
-      "content": "<|im_end|>",
+      "content": "<|end_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2050,12 +2050,17 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": null
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }