Text Generation
Transformers
Safetensors
llama
Not-For-All-Audiences
nsfw
text-generation-inference
Inference Endpoints
Upload folder using huggingface_hub
Browse files- config.json +27 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Undi95/Amethyst-13B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 40,
|
15 |
+
"num_hidden_layers": 40,
|
16 |
+
"num_key_value_heads": 40,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.33.2",
|
25 |
+
"use_cache": false,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
model-00001-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9c9a6c393e82ad8b3e64fadffb0367a793a7bb970592e2910163e0550d1d649
|
3 |
+
size 2417011552
|
model-00002-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af0b25b3b184cec500cda6e1d3248fb3398fc1db8c579c80ad6c9ea05fc84e3f
|
3 |
+
size 2044808592
|
model-00003-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa0bfedb165d7257c134b778f02042af63b87d77b5cb32bd0e583b16affb0879
|
3 |
+
size 2060516760
|
model-00004-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55f43401add71acb843c22320d2b6010a5aecd1e381eb0fae834451830fdba46
|
3 |
+
size 1955658944
|
model-00005-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32c68e270fcd793828ac03598ead08c402cd00853db3aad92472f177f7b1c24
|
3 |
+
size 2044787912
|
model-00006-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa91c2f9b9cc81a2cfba0c33c105c820b475f1d6539f8468f658f01fd3f76b91
|
3 |
+
size 2044787904
|
model-00007-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edfcbc3f61e71411fb7120209d51dbd21fe605c72f29e8ff920dd8fa11330f05
|
3 |
+
size 2044808624
|
model-00008-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86f439f3a96bef0ad07da6bda515fc98cb4a079590f63b8241863531fc6396d3
|
3 |
+
size 2060516792
|
model-00009-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bac295c9170325e25c580c669822306062aec698299cb5d7300bee8e95c8a5d4
|
3 |
+
size 1955658952
|
model-00010-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14775f3d01e4519c86c68b500e599a7015f1b2b841f1ac43d5962b0619158b23
|
3 |
+
size 2044787912
|
model-00011-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d98968872d4e89fcd3424df907854a360869a7739c438ba203ead14c25daa175
|
3 |
+
size 2044787904
|
model-00012-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5141f95c562360d517951590e441c5f3194616747991a912d46c0081d8f6c10
|
3 |
+
size 2044808624
|
model-00013-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c048abf41d94191f49dbef9884c430010271db483d657771783e9f0a9beaaf9
|
3 |
+
size 1924190472
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "lm_head.weight": "model-00013-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", "model.norm.weight": "model-00013-of-00013.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 4096,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"spaces_between_special_tokens": false,
|
27 |
+
"tokenizer_class": "LlamaTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"use_default_system_prompt": true
|
37 |
+
}
|