Update v1.0

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 language:
 - fr
-- en
 pipeline_tag: text-generation
 library_name: transformers
 tags:
@@ -16,17 +15,23 @@ inference: false
 
 # Vigogne-Falcon-7B-Chat: A French Chat Falcon Model
 
-Vigogne-Falcon-7B-Chat is a [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) model fine-tuned to conduct multi-turn dialogues in 🇫🇷 French between human user and AI assistant.
+Vigogne-Falcon-7B-Chat is a [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) model fine-tuned to conduct multi-turn dialogues in French between human user and AI assistant.
 
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
 
+## Changelog
+
+All versions are available in branches.
+
+- **V1.0**: Initial release.
+- **V2.0**: Expanded training dataset to 419k for better performance.
+
 ## Usage
 
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
-
-device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+from vigogne.preprocess import generate_inference_chat_prompt
 
 model_name_or_path = "bofenghuang/vigogne-falcon-7b-chat"
 
@@ -35,42 +40,30 @@ tokenizer.pad_token = tokenizer.eos_token
 
 model = AutoModelForCausalLM.from_pretrained(
     model_name_or_path,
-    load_in_8bit=False,
     torch_dtype=torch.float16,
     device_map="auto",
     trust_remote_code=True,
 )
 
-prompt_template = """Below is a conversation between a user and an AI assistant named Vigogne.
-Vigogne is an open-source AI assistant created by Zaion (https://zaion.ai/).
-Vigogne is polite, emotionally aware, humble-but-knowledgeable, always providing helpful and detailed answers.
-Vigogne is skilled in responding proficiently in the languages its users use and can perform a wide range of tasks such as text editing, translation, question answering, logical reasoning, coding, and many others.
-Vigogne cannot receive or generate audio or visual content and cannot access the internet.
-Vigogne strictly avoids discussing sensitive, offensive, illegal, ethical, or political topics and caveats when unsure of the answer.
-
-<|USER|>: Salut, assistant !
-<|ASSISTANT|>: Bonjour, que puis-je pour vous ?
-<|USER|>: {user_query}
-<|ASSISTANT|>: """
-
 user_query = "Expliquez la différence entre DoS et phishing."
-
-prompt = prompt_template.format(user_query=user_query)
-
-input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(device)
+prompt = generate_inference_chat_prompt([[user_query, ""]], tokenizer=tokenizer)
+input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
 input_length = input_ids.shape[1]
 
-generated_output = model.generate(
+generated_outputs = model.generate(
     input_ids=input_ids,
     generation_config=GenerationConfig(
-        max_new_tokens=512,
         temperature=0.1,
         do_sample=True,
+        repetition_penalty=1.0,
+        max_new_tokens=512,
     ),
+    return_dict_in_generate=True,
     pad_token_id=tokenizer.eos_token_id,
     eos_token_id=tokenizer.eos_token_id,
 )
-generated_text = tokenizer.decode(generated_output[0, input_length:], skip_special_tokens=True)
+generated_tokens = generated_outputs.sequences[0, input_length:]
+generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
 print(generated_text)
 ```
 

model-00003-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:75047a9cb9a5dba7a02bf88184d37be6449c361154a09af8386372cb1ce368a2
-size 912037008

model-00004-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa4ba9112d333b80487a0816398a5282ef0ec121439b856a9b570745e3fbeeba
-size 993465360

model-00005-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0fbadfeef0ba3cea219228863325db1f9f3f7fb6a33c98424ac2096f57940455
-size 993483736

model-00006-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:258e8528da4348ae48b9772dd437c52e4238585a04f8e34450daa1ec698201ef
-size 912037024

model-00007-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eadfaf1f3815eb7fa43abc155e1cd4ec70baccacda3d2fb8cbe5e620c624a32f
-size 993465368

model-00008-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6462725891e0ef6ad46d83ba1e767dc7414d2bc695c7221d2b0b10753c18d115
-size 993483760

model-00009-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e754491780c6f5eb6b4958713d253e4afff6d3e46fe4f6dd2e3ae6457b07b6a
-size 912037024

model-00010-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3264664651f553891daa7c81c0cf1ee939b8b577a101166a525c488a384ad8e9
-size 993465368

model-00011-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:586e8201593a4ec4d5b012fda59caf54a28ddab89279ae15f1016bc6711d8866
-size 993483760

model-00012-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06dbdb32dba861ff94677d0efdd236aeb65cbaf31a3d76f0e183c0741d8e39b5
-size 912037024

model-00013-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4c465997e40844d4557085223eb860318952c8cb695c7451a2cb4f978921395
-size 993465368

model-00014-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be80a3e1dad1a3b02c8d07a44cc967d1b89ee5da21972a0c8cf486c32076a39a
-size 993483760

model-00015-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11f02deaf0df2720fa918c6df9c809f1e27f298b9ac9c3bdafd722865c958434
-size 414140864

model.safetensors.index.json

@@ -1,202 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13843441408
-  },
-  "weight_map": {
-    "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
-    "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.1.input_layernorm.bias": "model-00002-of-00015.safetensors",
-    "transformer.h.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.self_attention.dense.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.10.input_layernorm.bias": "model-00005-of-00015.safetensors",
-    "transformer.h.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.10.self_attention.dense.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.10.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
-    "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
-    "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.12.self_attention.dense.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.13.input_layernorm.bias": "model-00007-of-00015.safetensors",
-    "transformer.h.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
-    "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.15.input_layernorm.bias": "model-00008-of-00015.safetensors",
-    "transformer.h.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.self_attention.dense.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
-    "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.input_layernorm.bias": "model-00008-of-00015.safetensors",
-    "transformer.h.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.17.self_attention.dense.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.17.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
-    "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
-    "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.19.self_attention.dense.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
-    "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.20.input_layernorm.bias": "model-00010-of-00015.safetensors",
-    "transformer.h.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
-    "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.22.input_layernorm.bias": "model-00011-of-00015.safetensors",
-    "transformer.h.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.self_attention.dense.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
-    "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.input_layernorm.bias": "model-00011-of-00015.safetensors",
-    "transformer.h.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.24.self_attention.dense.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.24.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
-    "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
-    "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.26.self_attention.dense.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.27.input_layernorm.bias": "model-00013-of-00015.safetensors",
-    "transformer.h.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
-    "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.29.input_layernorm.bias": "model-00014-of-00015.safetensors",
-    "transformer.h.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.self_attention.dense.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.3.input_layernorm.bias": "model-00002-of-00015.safetensors",
-    "transformer.h.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.3.self_attention.dense.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.3.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.30.input_layernorm.bias": "model-00014-of-00015.safetensors",
-    "transformer.h.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.self_attention.dense.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.input_layernorm.bias": "model-00014-of-00015.safetensors",
-    "transformer.h.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
-    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00015-of-00015.safetensors",
-    "transformer.h.31.self_attention.dense.weight": "model-00015-of-00015.safetensors",
-    "transformer.h.31.self_attention.query_key_value.weight": "model-00015-of-00015.safetensors",
-    "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
-    "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
-    "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.6.input_layernorm.bias": "model-00004-of-00015.safetensors",
-    "transformer.h.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
-    "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.8.input_layernorm.bias": "model-00005-of-00015.safetensors",
-    "transformer.h.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.self_attention.dense.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
-    "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
-    "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
-    "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
-    "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors"
-  }
-}

model-00001-of-00015.safetensors → pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17089ea2642991d894485e4d67107092fddcf47f787874446ae476ea3429eaa
-size 839895496
+oid sha256:ba14fd8ae7dd81cd6c4a2667143e9b85708f2170a45181fe8899c19f4b3c984e
+size 9951026273

model-00002-of-00015.safetensors → pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b22edfdfcbf8861771852a1272824e7dd42e5c6c98f5b44ce2f128e4e431cb
-size 993483752
+oid sha256:eecab6a6f509c162a23e992cb230da9bf710c1fd236aeec6c3de5d9477775a43
+size 4483420827

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 14434379520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}