CarlosJefte commited on
Commit
079c121
1 Parent(s): 3377d29

(Trained with Unsloth)

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "CarlosJefte/llama-3-8b-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -12,6 +12,7 @@
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
  "max_position_embeddings": 8192,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
@@ -22,7 +23,7 @@
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float16",
25
- "transformers_version": "4.40.2",
26
  "unsloth_version": "2024.5",
27
  "use_cache": true,
28
  "vocab_size": 128256
 
1
  {
2
+ "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
  "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 32,
 
23
  "rope_theta": 500000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float16",
26
+ "transformers_version": "4.41.0",
27
  "unsloth_version": "2024.5",
28
  "use_cache": true,
29
  "vocab_size": 128256
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "max_length": 4096,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
- "transformers_version": "4.40.2"
9
  }
 
5
  "max_length": 4096,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.41.0"
9
  }
pytorch_model-00001-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00671699fd791d23bae4268f1175c24205269884eee94984e4760a391d3bd518
3
  size 4976718466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae06e0f0d367d2ec3de6becc22dabfb9f95c3a6f9f6828183172fc2bef0b78b8
3
  size 4976718466
pytorch_model-00002-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de635975b441b840b0d33a746649fbe5377a88a22ae23ed6d555f50862bd11b2
3
  size 4999827206
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6329d9c353867159c431de1ab975e4c3288d25ac699b99a0baed05dbbabf6e7
3
  size 4999827206
pytorch_model-00003-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4694cf177e7f52fa4de31411978769b30eea7c79aa310493196fa7ea5094e442
3
  size 4915939082
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e581bd08158e48aaa9739a6175cc8052a9d099f634e43f88740645e9b1f570d7
3
  size 4915939082
pytorch_model-00004-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:292aa856d5a5c787cbede10d8f9894d42d23bb2d9060a18a5c95f989f86b8d41
3
  size 1168140873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42aec017a8e19a0d5da9d462ee5af3cfd1997f0f21ab9ac22c9dfb142c6cdfc9
3
  size 1168140873
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 8192,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -2058,7 +2058,7 @@
2058
  }
2059
  },
2060
  "bos_token": "<|begin_of_text|>",
2061
- "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 %}",
2062
  "clean_up_tokenization_spaces": true,
2063
  "eos_token": "<|end_of_text|>",
2064
  "model_input_names": [
 
2058
  }
2059
  },
2060
  "bos_token": "<|begin_of_text|>",
2061
+ "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 %}",
2062
  "clean_up_tokenization_spaces": true,
2063
  "eos_token": "<|end_of_text|>",
2064
  "model_input_names": [