Upload 7 files
Browse files- config.json +4 -4
- generation_config.json +7 -0
- model.safetensors +1 -1
- special_tokens_map.json +8 -1
- tokenizer.json +2 -2
- tokenizer_config.json +5 -3
config.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "SicariusSicariiStuff/
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id":
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 3072,
|
|
@@ -30,8 +30,8 @@
|
|
| 30 |
"rope_theta": 500000.0,
|
| 31 |
"tie_word_embeddings": false,
|
| 32 |
"torch_dtype": "bfloat16",
|
| 33 |
-
"transformers_version": "4.
|
| 34 |
-
"use_cache":
|
| 35 |
"vocab_size": 128256,
|
| 36 |
"quantization_config": {
|
| 37 |
"quant_method": "exl3",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "SicariusSicariiStuff/Impish_LLAMA_4B_V2",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128019,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 3072,
|
|
|
|
| 30 |
"rope_theta": 500000.0,
|
| 31 |
"tie_word_embeddings": false,
|
| 32 |
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"use_cache": false,
|
| 35 |
"vocab_size": 128256,
|
| 36 |
"quantization_config": {
|
| 37 |
"quant_method": "exl3",
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128019,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2019186224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec9d168e6c5ccf6841c81598bc719608862ac55caf494c98a2ccb15d3fad5f8f
|
| 3 |
size 2019186224
|
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,14 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
|
| 3 |
+
size 17209884
|
tokenizer_config.json
CHANGED
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"128018": {
|
| 148 |
-
"content": "<|
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
@@ -153,7 +153,7 @@
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"128019": {
|
| 156 |
-
"content": "<|
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
@@ -2050,13 +2050,15 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
-
"eos_token": "<|
|
| 2055 |
"extra_special_tokens": {},
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
|
|
|
| 2061 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 2062 |
}
|
|
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"128018": {
|
| 148 |
+
"content": "<|im_start|>",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"128019": {
|
| 156 |
+
"content": "<|im_end|>",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|im_end|>",
|
| 2056 |
"extra_special_tokens": {},
|
| 2057 |
"model_input_names": [
|
| 2058 |
"input_ids",
|
| 2059 |
"attention_mask"
|
| 2060 |
],
|
| 2061 |
"model_max_length": 131072,
|
| 2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2063 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 2064 |
}
|