(Trained with Unsloth)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "CarlosJefte/llama-3-8b-bnb-4bit",
+  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,7 +23,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.0",
   "unsloth_version": "2024.5",
   "use_cache": true,
   "vocab_size": 128256

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.0"
 }

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00671699fd791d23bae4268f1175c24205269884eee94984e4760a391d3bd518
+oid sha256:ae06e0f0d367d2ec3de6becc22dabfb9f95c3a6f9f6828183172fc2bef0b78b8
 size 4976718466

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de635975b441b840b0d33a746649fbe5377a88a22ae23ed6d555f50862bd11b2
+oid sha256:b6329d9c353867159c431de1ab975e4c3288d25ac699b99a0baed05dbbabf6e7
 size 4999827206

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4694cf177e7f52fa4de31411978769b30eea7c79aa310493196fa7ea5094e442
+oid sha256:e581bd08158e48aaa9739a6175cc8052a9d099f634e43f88740645e9b1f570d7
 size 4915939082

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292aa856d5a5c787cbede10d8f9894d42d23bb2d9060a18a5c95f989f86b8d41
+oid sha256:42aec017a8e19a0d5da9d462ee5af3cfd1997f0f21ab9ac22c9dfb142c6cdfc9
 size 1168140873

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8192,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -2058,7 +2058,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "tokenizer.chat_template = {% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ bos_token + '<|user|>\n' + message['content'].strip() + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ bos_token + '<|system|>\n' + message['content'].strip() + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ bos_token + '<|assistant|>\n' + message['content'].strip() + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "chat_template": "{{ \"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\" }}\n{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Input:\n' + message['content'].strip() }}\n{% elif message['role'] == 'system' %}\n{{ '### Instruction:\n' + message['content'].strip() }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Response:\n' + message['content'].strip() + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Response:\n' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [