Upload folder using huggingface_hub
Browse files- README.md +42 -0
- config.json +36 -0
- mergekit_config.yml +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 +1 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +46 -0
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- LeroyDyer/Mixtral_AI_128k_bioMedical
|
4 |
+
- filipealmeida/Mistral-7B-Instruct-v0.1-sharded
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# MODEL_NAME
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [LeroyDyer/Mixtral_AI_128k_bioMedical](https://huggingface.co/LeroyDyer/Mixtral_AI_128k_bioMedical)
|
24 |
+
* [filipealmeida/Mistral-7B-Instruct-v0.1-sharded](https://huggingface.co/filipealmeida/Mistral-7B-Instruct-v0.1-sharded)
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
|
32 |
+
models:
|
33 |
+
- model: LeroyDyer/Mixtral_AI_128k_bioMedical
|
34 |
+
parameters:
|
35 |
+
weight: 1.6128
|
36 |
+
- model: filipealmeida/Mistral-7B-Instruct-v0.1-sharded
|
37 |
+
parameters:
|
38 |
+
weight: 0.3312
|
39 |
+
merge_method: linear
|
40 |
+
dtype: float16
|
41 |
+
|
42 |
+
```
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "LeroyDyer/Mixtral_AI_128k_bioMedical",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "NousResearch/Yarn-Mistral-7b-128k--configuration_mistral.MistralConfig",
|
8 |
+
"AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-128k--modeling_mistral_yarn.MistralForCausalLM"
|
9 |
+
},
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 14336,
|
16 |
+
"max_position_embeddings": 32768,
|
17 |
+
"max_sequence_length": 131072,
|
18 |
+
"model_type": "mistral",
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_hidden_layers": 32,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": {
|
24 |
+
"factor": 16.0,
|
25 |
+
"finetuned": true,
|
26 |
+
"original_max_position_embeddings": 8192,
|
27 |
+
"type": "yarn"
|
28 |
+
},
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 131072,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "float16",
|
33 |
+
"transformers_version": "4.38.2",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 32000
|
36 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: LeroyDyer/Mixtral_AI_128k_bioMedical
|
4 |
+
parameters:
|
5 |
+
weight: 1.6128
|
6 |
+
- model: filipealmeida/Mistral-7B-Instruct-v0.1-sharded
|
7 |
+
parameters:
|
8 |
+
weight: 0.3312
|
9 |
+
merge_method: linear
|
10 |
+
dtype: float16
|
model-00001-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a07f2699569396b360b8c2723d33e4b7a4c70d3e189b4d455d762cc17370535
|
3 |
+
size 1912664448
|
model-00002-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bc512a0f98f8a488b68af10877696e25c86ccb32c99fdac333abc52a249fd2
|
3 |
+
size 1979773552
|
model-00003-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aebbd7c5f88d02a4d33768002c637c981bcd88b7496c3fea8e790c7520d3cd63
|
3 |
+
size 1979798016
|
model-00004-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422c6514a9f75173aea2d760b598b2400c64da87d09d52e5e25c6fca4888042f
|
3 |
+
size 1946227288
|
model-00005-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3ddd4672fe6d5c9dbcf41f3f0cf9cd1cce1c50e663f96c19a451410f6038c3b
|
3 |
+
size 1744908480
|
model-00006-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c1f2ebcf3a287f25e365b7aa6635476061dc4403658c0dc0a2434f4ba5849e
|
3 |
+
size 1889587040
|
model-00007-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54066a7b27adab817b286e71f01b30b20ec218b455ce2ba4fd8c6c091fdc5d18
|
3 |
+
size 1998671664
|
model-00008-of-00008.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d59ae31de74a9714cf36ccf499421bc7c71c895ef46db23c9799dd85cd2a8532
|
3 |
+
size 1031867184
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.embed_tokens.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"unk_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": null,
|
41 |
+
"sp_model_kwargs": {},
|
42 |
+
"spaces_between_special_tokens": false,
|
43 |
+
"tokenizer_class": "LlamaTokenizer",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": true
|
46 |
+
}
|