Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +47 -0
- generation_config.json +8 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
|
3 |
+
"architectures": [
|
4 |
+
"Gemma2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attn_logit_softcapping": 50.0,
|
9 |
+
"bos_token_id": 2,
|
10 |
+
"cache_implementation": "hybrid",
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"final_logit_softcapping": 30.0,
|
13 |
+
"head_dim": 256,
|
14 |
+
"hidden_act": "gelu_pytorch_tanh",
|
15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
16 |
+
"hidden_size": 3584,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 14336,
|
19 |
+
"max_position_embeddings": 8192,
|
20 |
+
"model_type": "gemma2",
|
21 |
+
"num_attention_heads": 16,
|
22 |
+
"num_hidden_layers": 42,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"quantization_config": {
|
26 |
+
"bnb_4bit_compute_dtype": "float16",
|
27 |
+
"bnb_4bit_quant_type": "nf4",
|
28 |
+
"bnb_4bit_use_double_quant": true,
|
29 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
+
"llm_int8_has_fp16_weight": false,
|
31 |
+
"llm_int8_skip_modules": null,
|
32 |
+
"llm_int8_threshold": 6.0,
|
33 |
+
"load_in_4bit": true,
|
34 |
+
"load_in_8bit": false,
|
35 |
+
"quant_method": "bitsandbytes"
|
36 |
+
},
|
37 |
+
"query_pre_attn_scalar": 256,
|
38 |
+
"rms_norm_eps": 1e-06,
|
39 |
+
"rope_theta": 10000.0,
|
40 |
+
"sliding_window": 4096,
|
41 |
+
"sliding_window_size": 4096,
|
42 |
+
"torch_dtype": "float16",
|
43 |
+
"transformers_version": "4.42.3",
|
44 |
+
"unsloth_version": "2024.7",
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 256000
|
47 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"cache_implementation": "hybrid",
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.42.3"
|
8 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4538ba8ac4e9e0ef5fc5d6f5e8b900f756a743f24a671028fced57d08ed4937c
|
3 |
+
size 4979448150
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3d796db428b5ca580d6d9c8ce1839ec6d3c0a4f739dc1059b273846bc508d13
|
3 |
+
size 1151730981
|
pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|