Upload folder using huggingface_hub
Browse files- config.json +4 -31
- generation_config.json +11 -4
- model.safetensors +3 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +2 -3
config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 896,
|
|
@@ -15,42 +16,14 @@
|
|
| 15 |
"num_attention_heads": 14,
|
| 16 |
"num_hidden_layers": 24,
|
| 17 |
"num_key_value_heads": 2,
|
| 18 |
-
"pad_token_id": 151654,
|
| 19 |
-
"quantization_config": {
|
| 20 |
-
"_load_in_4bit": true,
|
| 21 |
-
"_load_in_8bit": false,
|
| 22 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 23 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 24 |
-
"bnb_4bit_quant_type": "nf4",
|
| 25 |
-
"bnb_4bit_use_double_quant": true,
|
| 26 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 27 |
-
"llm_int8_has_fp16_weight": false,
|
| 28 |
-
"llm_int8_skip_modules": [
|
| 29 |
-
"lm_head",
|
| 30 |
-
"multi_modal_projector",
|
| 31 |
-
"merger",
|
| 32 |
-
"modality_projection",
|
| 33 |
-
"model.layers.0.self_attn",
|
| 34 |
-
"model.layers.0.mlp",
|
| 35 |
-
"model.layers.2.mlp",
|
| 36 |
-
"model.layers.3.mlp",
|
| 37 |
-
"model.layers.21.mlp",
|
| 38 |
-
"model.layers.0.self_attn.q_proj"
|
| 39 |
-
],
|
| 40 |
-
"llm_int8_threshold": 6.0,
|
| 41 |
-
"load_in_4bit": true,
|
| 42 |
-
"load_in_8bit": false,
|
| 43 |
-
"quant_method": "bitsandbytes"
|
| 44 |
-
},
|
| 45 |
"rms_norm_eps": 1e-06,
|
| 46 |
"rope_scaling": null,
|
| 47 |
"rope_theta": 1000000.0,
|
| 48 |
-
"sliding_window":
|
| 49 |
"tie_word_embeddings": true,
|
| 50 |
"torch_dtype": "bfloat16",
|
| 51 |
-
"transformers_version": "4.49.0
|
| 52 |
-
"unsloth_fixed": true,
|
| 53 |
"use_cache": true,
|
| 54 |
"use_sliding_window": false,
|
| 55 |
"vocab_size": 151936
|
| 56 |
-
}
|
|
|
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 896,
|
|
|
|
| 16 |
"num_attention_heads": 14,
|
| 17 |
"num_hidden_layers": 24,
|
| 18 |
"num_key_value_heads": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"rms_norm_eps": 1e-06,
|
| 20 |
"rope_scaling": null,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": 32768,
|
| 23 |
"tie_word_embeddings": true,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.49.0",
|
|
|
|
| 26 |
"use_cache": true,
|
| 27 |
"use_sliding_window": false,
|
| 28 |
"vocab_size": 151936
|
| 29 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"transformers_version": "4.49.0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
"transformers_version": "4.49.0"
|
| 14 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:557175c8712976113bfa0d9f2ad9c32257480114062a74af2ce3a9254fb92f33
|
| 3 |
+
size 988097824
|
special_tokens_map.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
-
"content": "<|
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
|
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -200,9 +200,8 @@
|
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
-
"model_max_length":
|
| 204 |
-
"pad_token": "<|
|
| 205 |
-
"padding_side": "left",
|
| 206 |
"split_special_tokens": false,
|
| 207 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
"unk_token": null
|
|
|
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
|
|
|
| 205 |
"split_special_tokens": false,
|
| 206 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
"unk_token": null
|