Commit
·
ec4be89
1
Parent(s):
da15dea
Upload LlamaForCausalLM
Browse files- config.json +52 -0
- generation_config.json +10 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-2-70b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 80,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"quantization_config": {
|
21 |
+
"batch_size": 1,
|
22 |
+
"bits": 4,
|
23 |
+
"block_name_to_quantize": null,
|
24 |
+
"cache_block_outputs": true,
|
25 |
+
"damp_percent": 0.1,
|
26 |
+
"dataset": "c4",
|
27 |
+
"desc_act": false,
|
28 |
+
"exllama_config": {
|
29 |
+
"version": 1
|
30 |
+
},
|
31 |
+
"group_size": 128,
|
32 |
+
"max_input_length": null,
|
33 |
+
"model_seqlen": null,
|
34 |
+
"module_name_preceding_first_block": null,
|
35 |
+
"modules_in_block_to_quantize": null,
|
36 |
+
"pad_token_id": null,
|
37 |
+
"quant_method": "gptq",
|
38 |
+
"sym": true,
|
39 |
+
"tokenizer": null,
|
40 |
+
"true_sequential": true,
|
41 |
+
"use_cuda_fp16": false,
|
42 |
+
"use_exllama": true
|
43 |
+
},
|
44 |
+
"rms_norm_eps": 1e-05,
|
45 |
+
"rope_scaling": null,
|
46 |
+
"rope_theta": 10000.0,
|
47 |
+
"tie_word_embeddings": false,
|
48 |
+
"torch_dtype": "float16",
|
49 |
+
"transformers_version": "4.37.0.dev0",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 32000
|
52 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.37.0.dev0"
|
10 |
+
}
|
model-00001-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66a31eebd66d51ca9b25c12ead28705cbec9bc72d801eb5007a84c59ffc26068
|
3 |
+
size 4979149736
|
model-00002-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6876b136db1f26bd65253ab80cab84bd77ab0c46430d7bad96f69fe45d54ba54
|
3 |
+
size 4969738608
|
model-00003-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11c2de371c7b4cbca19c21c33f310c67d24d79b78a732e8b199f795238cdc6ff
|
3 |
+
size 4895515352
|
model-00004-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ca84751042f0210a4be3749eb8346364e6832cfa1a7d1e4fcc6c8b9bd9480a
|
3 |
+
size 4895515352
|
model-00005-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:522cc13724b831cbe16cefda07e860d791fed9a4a4ccb646d682927f0e1587ba
|
3 |
+
size 4895515352
|
model-00006-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94cca3dabe75127951793f97db8453000dfd256408abf8e589c44aca0cacdf8d
|
3 |
+
size 4895515352
|
model-00007-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4225a99eb9152b6fb2cc7177377c01b93c875cb35338da6480969ca82136b8d0
|
3 |
+
size 4895515352
|
model-00008-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83cbaa3701f805d4c9f635354b5e1a6f863fc3fb07edbc923046713a538858a6
|
3 |
+
size 2225875144
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|