Upload MixtralForCausalLM
Browse files- config.json +46 -0
- generation_config.json +6 -0
- model-00001-of-00017.safetensors +3 -0
- model-00002-of-00017.safetensors +3 -0
- model-00003-of-00017.safetensors +3 -0
- model-00004-of-00017.safetensors +3 -0
- model-00005-of-00017.safetensors +3 -0
- model-00006-of-00017.safetensors +3 -0
- model-00007-of-00017.safetensors +3 -0
- model-00008-of-00017.safetensors +3 -0
- model-00009-of-00017.safetensors +3 -0
- model-00010-of-00017.safetensors +3 -0
- model-00011-of-00017.safetensors +3 -0
- model-00012-of-00017.safetensors +3 -0
- model-00013-of-00017.safetensors +3 -0
- model-00014-of-00017.safetensors +3 -0
- model-00015-of-00017.safetensors +3 -0
- model-00016-of-00017.safetensors +3 -0
- model-00017-of-00017.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "float32",
|
25 |
+
"bnb_4bit_quant_storage": "uint8",
|
26 |
+
"bnb_4bit_quant_type": "fp4",
|
27 |
+
"bnb_4bit_use_double_quant": false,
|
28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
+
"llm_int8_has_fp16_weight": false,
|
30 |
+
"llm_int8_skip_modules": null,
|
31 |
+
"llm_int8_threshold": 6.0,
|
32 |
+
"load_in_4bit": true,
|
33 |
+
"load_in_8bit": false,
|
34 |
+
"quant_method": "bitsandbytes"
|
35 |
+
},
|
36 |
+
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_theta": 1000000,
|
38 |
+
"router_aux_loss_coef": 0.001,
|
39 |
+
"router_jitter_noise": 0.0,
|
40 |
+
"sliding_window": null,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "float16",
|
43 |
+
"transformers_version": "4.40.0.dev0",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 32000
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.40.0.dev0"
|
6 |
+
}
|
model-00001-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb849d8c50c706bd53a5d3f846a22c1c5400aa5d5986dd41a1e2d6692019115
|
3 |
+
size 4951626618
|
model-00002-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38ffc7c25d66675bf64f51a8cd494b4ae86ee1e9c92c1a3fb46c91f51f4291ad
|
3 |
+
size 4961824784
|
model-00003-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a473dd813bef1a762afef2b484ade87cf285c18510b271e43c47597e717987c
|
3 |
+
size 4954801840
|
model-00004-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09af1d3bb8c947c7419c91ca79ff47ade0d6ccb1afe934ad6f13852fea19a632
|
3 |
+
size 4961825192
|
model-00005-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da2872347bb2ef118c87c0f614993a4d4d1f9948e2e10c516c330a6a689fce0b
|
3 |
+
size 4954802256
|
model-00006-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c6179b62993674bcf85b2f69d1b938dec3202e69d4423277a0f5c20cd83c2f4
|
3 |
+
size 4961825192
|
model-00007-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa529c2f6b145fb52a2554ac7b67e7d1c0a4bf9066ac25d4a5ac301e8d84adf6
|
3 |
+
size 4954802256
|
model-00008-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9ded0880967c3c4fbb11f5d9eb0416f9c76264ea20614bd75abf5ac94d70d0
|
3 |
+
size 4961825192
|
model-00009-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dcac14937afd8744a2404177ad3fc0400af8a89f82f424dcdf4e547404d2c7d
|
3 |
+
size 4954802256
|
model-00010-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0adbb11ef8413619d47953d8f79015fe4e6707f3652881fe53c28afd756db4ee
|
3 |
+
size 4961825192
|
model-00011-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:804e7a905a6826b21b252fc8341b5a1de0942778ce6eecaa8c41c9186dea029f
|
3 |
+
size 4954802256
|
model-00012-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7846742154eaf7ecbcdf540ecf93d3ca7af0073f4d6b9ff8cc574be646a6a33d
|
3 |
+
size 4961825192
|
model-00013-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:701f2d9375c7faa32c07a11547414fa15c95fecfb796999a4b497ff51a2e06f2
|
3 |
+
size 4954802256
|
model-00014-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b0731d0ef5165ec76c7a473602272662fb638ca74f3359a42cc5ab830aea6d1
|
3 |
+
size 4990163459
|
model-00015-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:062db6e6546c37e3a45485c0abcd62f273b14d61c69aaab466f9fe2043f09b1c
|
3 |
+
size 4983087791
|
model-00016-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f66c9aab5928deb8a5725e665fa11e1013cc4b67baed9e08659405071c0e7cb7
|
3 |
+
size 4848614772
|
model-00017-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e110af919cb6ea1a47ae33dea0ee3e597b6ed9bd851632a34aea547bf3d4a269
|
3 |
+
size 393216128
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|