Zelknight463
commited on
Commit
•
022dec6
1
Parent(s):
75c6664
Upload folder using huggingface_hub
Browse files- README.md +62 -0
- config.json +32 -0
- mergekit_config.yml +16 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +193 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- deepseek-ai/deepseek-coder-6.7b-instruct
|
4 |
+
- m-a-p/OpenCodeInterpreter-DS-6.7B
|
5 |
+
tags:
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- deepseek-ai/deepseek-coder-6.7b-instruct
|
10 |
+
- m-a-p/OpenCodeInterpreter-DS-6.7B
|
11 |
+
---
|
12 |
+
|
13 |
+
# deepseek-coder-ties
|
14 |
+
|
15 |
+
deepseek-coder-ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct)
|
17 |
+
* [m-a-p/OpenCodeInterpreter-DS-6.7B](https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-6.7B)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
models:
|
23 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
24 |
+
parameters:
|
25 |
+
density: [1, 0.7, 0.1] # density gradient
|
26 |
+
weight: 1.0
|
27 |
+
- model: m-a-p/OpenCodeInterpreter-DS-6.7B
|
28 |
+
parameters:
|
29 |
+
density: 0.5
|
30 |
+
weight: [0, 0.3, 0.7, 1] # weight gradient
|
31 |
+
merge_method: ties
|
32 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
33 |
+
parameters:
|
34 |
+
normalize: true
|
35 |
+
int8_mask: true
|
36 |
+
dtype: float16
|
37 |
+
```
|
38 |
+
|
39 |
+
## 💻 Usage
|
40 |
+
|
41 |
+
```python
|
42 |
+
!pip install -qU transformers accelerate
|
43 |
+
|
44 |
+
from transformers import AutoTokenizer
|
45 |
+
import transformers
|
46 |
+
import torch
|
47 |
+
|
48 |
+
model = "Zelknight463/deepseek-coder-ties"
|
49 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
52 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
53 |
+
pipeline = transformers.pipeline(
|
54 |
+
"text-generation",
|
55 |
+
model=model,
|
56 |
+
torch_dtype=torch.float16,
|
57 |
+
device_map="auto",
|
58 |
+
)
|
59 |
+
|
60 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
61 |
+
print(outputs[0]["generated_text"])
|
62 |
+
```
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 32013,
|
9 |
+
"eos_token_id": 32014,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-06,
|
22 |
+
"rope_scaling": {
|
23 |
+
"factor": 4.0,
|
24 |
+
"type": "linear"
|
25 |
+
},
|
26 |
+
"rope_theta": 100000,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float16",
|
29 |
+
"transformers_version": "4.42.3",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32256
|
32 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
4 |
+
parameters:
|
5 |
+
density: [1, 0.7, 0.1] # density gradient
|
6 |
+
weight: 1.0
|
7 |
+
- model: m-a-p/OpenCodeInterpreter-DS-6.7B
|
8 |
+
parameters:
|
9 |
+
density: 0.5
|
10 |
+
weight: [0, 0.3, 0.7, 1] # weight gradient
|
11 |
+
merge_method: ties
|
12 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
13 |
+
parameters:
|
14 |
+
normalize: true
|
15 |
+
int8_mask: true
|
16 |
+
dtype: float16
|
model-00001-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:056f1fe8680a77c23b9777172af17571876d8f3e10d39f89720e9f404f02d519
|
3 |
+
size 933258568
|
model-00002-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52aec48232c5b45b00145c80e164a8bd83f99bdfae4412f71ef4577dbdfd875
|
3 |
+
size 989890808
|
model-00003-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623f31a6fcf184c7f43c7d8cd3e5a43fcbc5766f896c88040d358ebff4229697
|
3 |
+
size 966830568
|
model-00004-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:835c3fad2ad2fef4b03230d0739891a23132009a51b63cd02a9f4d65cac6972a
|
3 |
+
size 966830560
|
model-00005-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4312e66955c5f73daf759292df19b06aab3f928a69f8f8f087a2adea7c4e85e2
|
3 |
+
size 989899128
|
model-00006-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab63a6ea92c444a7a58581db4e9beeaaa291fc44b4015667b572b877b23210a8
|
3 |
+
size 943762000
|
model-00007-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a02d3a81df9f50507c088a298b51cec614f785cec229eedc48652243e228918
|
3 |
+
size 989890816
|
model-00008-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65bb6461bcaa9bc25a7e72e279c18b9cb95ab29e61e0a9513497323f28ac9fe1
|
3 |
+
size 966830568
|
model-00009-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb38cd6285d442c234b0ec364a9b4823a6d7830ec86854e644ae6c89b7d36b10
|
3 |
+
size 966830560
|
model-00010-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cd134965769491a57043a6c4f0fcee4ad0dfc85f9f6dd9821892e79a1b29076
|
3 |
+
size 989899128
|
model-00011-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf5dd4b2a5e00c6dcb4683bb1cea6f7cdd5e691e2db3f14583a4c7fb5991ac96
|
3 |
+
size 943762000
|
model-00012-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18db9fbb7ec6745d979a48c5d65063a6b37e05c64b059646a2f59c119db59e1a
|
3 |
+
size 989890808
|
model-00013-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c13e4c484391b32a321eb01b362a330521bddc08ab13ff9808828f19600ff4
|
3 |
+
size 966830552
|
model-00014-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5783fc7910567a7a9fcba580a77b66cc79f305462c27275c314504a8abaf33b
|
3 |
+
size 876652872
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 13481025536}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"32000": {
|
7 |
+
"content": "õ",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": false
|
13 |
+
},
|
14 |
+
"32001": {
|
15 |
+
"content": "÷",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": false
|
21 |
+
},
|
22 |
+
"32002": {
|
23 |
+
"content": "Á",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32003": {
|
31 |
+
"content": "ý",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"32004": {
|
39 |
+
"content": "À",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"32005": {
|
47 |
+
"content": "ÿ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"32006": {
|
55 |
+
"content": "ø",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"32007": {
|
63 |
+
"content": "ú",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"32008": {
|
71 |
+
"content": "þ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"32009": {
|
79 |
+
"content": "ü",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"32010": {
|
87 |
+
"content": "ù",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"32011": {
|
95 |
+
"content": "ö",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"32012": {
|
103 |
+
"content": "û",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"32013": {
|
111 |
+
"content": "<|begin▁of▁sentence|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32014": {
|
119 |
+
"content": "<|end▁of▁sentence|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32015": {
|
127 |
+
"content": "<|fim▁hole|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"32016": {
|
135 |
+
"content": "<|fim▁begin|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"32017": {
|
143 |
+
"content": "<|fim▁end|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"32018": {
|
151 |
+
"content": "<pad>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"32019": {
|
159 |
+
"content": "<|User|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"32020": {
|
167 |
+
"content": "<|Assistant|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"32021": {
|
175 |
+
"content": "<|EOT|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
}
|
182 |
+
},
|
183 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
184 |
+
"clean_up_tokenization_spaces": false,
|
185 |
+
"eos_token": "<|end▁of▁sentence|>",
|
186 |
+
"legacy": true,
|
187 |
+
"model_max_length": 16384,
|
188 |
+
"pad_token": "<|end▁of▁sentence|>",
|
189 |
+
"sp_model_kwargs": {},
|
190 |
+
"tokenizer_class": "LlamaTokenizer",
|
191 |
+
"unk_token": null,
|
192 |
+
"use_default_system_prompt": false
|
193 |
+
}
|