Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +54 -0
- generation_config.json +12 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ApertusForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 68,
|
| 10 |
+
"hidden_act": "xielu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 21504,
|
| 15 |
+
"max_position_embeddings": 65536,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "apertus",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 3,
|
| 22 |
+
"post_norm": false,
|
| 23 |
+
"qk_norm": true,
|
| 24 |
+
"quantization_config": {
|
| 25 |
+
"_load_in_4bit": true,
|
| 26 |
+
"_load_in_8bit": false,
|
| 27 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 28 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 29 |
+
"bnb_4bit_quant_type": "nf4",
|
| 30 |
+
"bnb_4bit_use_double_quant": true,
|
| 31 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 32 |
+
"llm_int8_has_fp16_weight": false,
|
| 33 |
+
"llm_int8_skip_modules": null,
|
| 34 |
+
"llm_int8_threshold": 6.0,
|
| 35 |
+
"load_in_4bit": true,
|
| 36 |
+
"load_in_8bit": false,
|
| 37 |
+
"quant_method": "bitsandbytes"
|
| 38 |
+
},
|
| 39 |
+
"rms_norm_eps": 1e-05,
|
| 40 |
+
"rope_scaling": {
|
| 41 |
+
"factor": 8.0,
|
| 42 |
+
"high_freq_factor": 4.0,
|
| 43 |
+
"low_freq_factor": 1.0,
|
| 44 |
+
"original_max_position_embeddings": 8192,
|
| 45 |
+
"rope_type": "llama3",
|
| 46 |
+
"type": "llama3"
|
| 47 |
+
},
|
| 48 |
+
"rope_theta": 12000000,
|
| 49 |
+
"tie_word_embeddings": false,
|
| 50 |
+
"transformers_version": "4.56.0",
|
| 51 |
+
"unsloth_version": "2025.8.10",
|
| 52 |
+
"use_cache": false,
|
| 53 |
+
"vocab_size": 131072
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2,
|
| 6 |
+
68,
|
| 7 |
+
72
|
| 8 |
+
],
|
| 9 |
+
"max_length": 65536,
|
| 10 |
+
"pad_token_id": 3,
|
| 11 |
+
"transformers_version": "4.56.0"
|
| 12 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64b6a89063c14cedfad5b17164b7d6b19eae46830bff31070df74c758bc23440
|
| 3 |
+
size 4675115617
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3d598e17c68d6e2921ccffdb74265280a9f8fefc4cdf9463b32597f2b6670bc
|
| 3 |
+
size 1073741952
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|