963138ebaee1b3b0c67b8861abb0ea5025ac1bca6e4e94ca1bfb23fac9aa6161
Browse files- README.md +86 -0
- added_tokens.json +66 -0
- config.json +28 -0
- model.safetensors.index.json +226 -0
- special_tokens_map.json +95 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +624 -0
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: pints-ai/1.5-Pints-2K-v0.1
|
3 |
+
datasets:
|
4 |
+
- pints-ai/Expository-Prose-V1
|
5 |
+
- HuggingFaceH4/ultrachat_200k
|
6 |
+
- Open-Orca/SlimOrca-Dedup
|
7 |
+
- meta-math/MetaMathQA
|
8 |
+
- HuggingFaceH4/deita-10k-v0-sft
|
9 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
10 |
+
- togethercomputer/llama-instruct
|
11 |
+
- LDJnr/Capybara
|
12 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
13 |
+
language:
|
14 |
+
- en
|
15 |
+
license: mit
|
16 |
+
pipeline_tag: text-generation
|
17 |
+
tags:
|
18 |
+
- mlx
|
19 |
+
extra_gated_prompt: Though best efforts has been made to ensure, as much as possible,
|
20 |
+
that all texts in the training corpora are royalty free, this does not constitute
|
21 |
+
a legal guarantee that such is the case. **By using any of the models, corpora or
|
22 |
+
part thereof, the user agrees to bear full responsibility to do the necessary due
|
23 |
+
diligence to ensure that he / she is in compliance with their local copyright laws.
|
24 |
+
Additionally, the user agrees to bear any damages arising as a direct cause (or
|
25 |
+
otherwise) of using any artifacts released by the pints research team, as well as
|
26 |
+
full responsibility for the consequences of his / her usage (or implementation)
|
27 |
+
of any such released artifacts. The user also indemnifies Pints Research Team (and
|
28 |
+
any of its members or agents) of any damage, related or unrelated, to the release
|
29 |
+
or subsequent usage of any findings, artifacts or code by the team. For the avoidance
|
30 |
+
of doubt, any artifacts released by the Pints Research team are done so in accordance
|
31 |
+
with the 'fair use' clause of Copyright Law, in hopes that this will aid the research
|
32 |
+
community in bringing LLMs to the next frontier.
|
33 |
+
extra_gated_fields:
|
34 |
+
Company: text
|
35 |
+
Country: country
|
36 |
+
Specific date: date_picker
|
37 |
+
I want to use this model for:
|
38 |
+
type: select
|
39 |
+
options:
|
40 |
+
- Research
|
41 |
+
- Education
|
42 |
+
- label: Other
|
43 |
+
value: other
|
44 |
+
I agree to use this model for in accordance to the afore-mentioned Terms of Use: checkbox
|
45 |
+
model-index:
|
46 |
+
- name: 1.5-Pints
|
47 |
+
results:
|
48 |
+
- task:
|
49 |
+
type: text-generation
|
50 |
+
dataset:
|
51 |
+
name: MTBench
|
52 |
+
type: ai2_arc
|
53 |
+
metrics:
|
54 |
+
- type: LLM-as-a-Judge
|
55 |
+
value: 3.73
|
56 |
+
name: MTBench
|
57 |
+
source:
|
58 |
+
url: https://huggingface.co/spaces/lmsys/mt-bench
|
59 |
+
name: MTBench
|
60 |
+
---
|
61 |
+
|
62 |
+
# mlx-community/1.5-Pints-2K-v0.1
|
63 |
+
|
64 |
+
The Model [mlx-community/1.5-Pints-2K-v0.1](https://huggingface.co/mlx-community/1.5-Pints-2K-v0.1) was converted to MLX format from [pints-ai/1.5-Pints-2K-v0.1](https://huggingface.co/pints-ai/1.5-Pints-2K-v0.1) using mlx-lm version **0.19.2**.
|
65 |
+
|
66 |
+
## Use with mlx
|
67 |
+
|
68 |
+
```bash
|
69 |
+
pip install mlx-lm
|
70 |
+
```
|
71 |
+
|
72 |
+
```python
|
73 |
+
from mlx_lm import load, generate
|
74 |
+
|
75 |
+
model, tokenizer = load("mlx-community/1.5-Pints-2K-v0.1")
|
76 |
+
|
77 |
+
prompt="hello"
|
78 |
+
|
79 |
+
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
80 |
+
messages = [{"role": "user", "content": prompt}]
|
81 |
+
prompt = tokenizer.apply_chat_template(
|
82 |
+
messages, tokenize=False, add_generation_prompt=True
|
83 |
+
)
|
84 |
+
|
85 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
86 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32003,
|
3 |
+
"<</SYS>>": 32007,
|
4 |
+
"<<SYS>>": 32006,
|
5 |
+
"<|assistant|>": 32010,
|
6 |
+
"<|begin_of_text|>": 32011,
|
7 |
+
"<|end_header_id|>": 32013,
|
8 |
+
"<|end_of_turn|>": 32000,
|
9 |
+
"<|eot_id|>": 32014,
|
10 |
+
"<|im_start|>": 32002,
|
11 |
+
"<|pad|>": 32001,
|
12 |
+
"<|reserved_0|>": 32015,
|
13 |
+
"<|reserved_10|>": 32025,
|
14 |
+
"<|reserved_11|>": 32026,
|
15 |
+
"<|reserved_12|>": 32027,
|
16 |
+
"<|reserved_13|>": 32028,
|
17 |
+
"<|reserved_14|>": 32029,
|
18 |
+
"<|reserved_15|>": 32030,
|
19 |
+
"<|reserved_16|>": 32031,
|
20 |
+
"<|reserved_17|>": 32032,
|
21 |
+
"<|reserved_18|>": 32033,
|
22 |
+
"<|reserved_19|>": 32034,
|
23 |
+
"<|reserved_1|>": 32016,
|
24 |
+
"<|reserved_20|>": 32035,
|
25 |
+
"<|reserved_21|>": 32036,
|
26 |
+
"<|reserved_22|>": 32037,
|
27 |
+
"<|reserved_23|>": 32038,
|
28 |
+
"<|reserved_24|>": 32039,
|
29 |
+
"<|reserved_25|>": 32040,
|
30 |
+
"<|reserved_26|>": 32041,
|
31 |
+
"<|reserved_27|>": 32042,
|
32 |
+
"<|reserved_28|>": 32043,
|
33 |
+
"<|reserved_29|>": 32044,
|
34 |
+
"<|reserved_2|>": 32017,
|
35 |
+
"<|reserved_30|>": 32045,
|
36 |
+
"<|reserved_31|>": 32046,
|
37 |
+
"<|reserved_32|>": 32047,
|
38 |
+
"<|reserved_33|>": 32048,
|
39 |
+
"<|reserved_34|>": 32049,
|
40 |
+
"<|reserved_35|>": 32050,
|
41 |
+
"<|reserved_36|>": 32051,
|
42 |
+
"<|reserved_37|>": 32052,
|
43 |
+
"<|reserved_38|>": 32053,
|
44 |
+
"<|reserved_39|>": 32054,
|
45 |
+
"<|reserved_3|>": 32018,
|
46 |
+
"<|reserved_40|>": 32055,
|
47 |
+
"<|reserved_41|>": 32056,
|
48 |
+
"<|reserved_42|>": 32057,
|
49 |
+
"<|reserved_43|>": 32058,
|
50 |
+
"<|reserved_44|>": 32059,
|
51 |
+
"<|reserved_45|>": 32060,
|
52 |
+
"<|reserved_46|>": 32061,
|
53 |
+
"<|reserved_47|>": 32062,
|
54 |
+
"<|reserved_48|>": 32063,
|
55 |
+
"<|reserved_4|>": 32019,
|
56 |
+
"<|reserved_5|>": 32020,
|
57 |
+
"<|reserved_6|>": 32021,
|
58 |
+
"<|reserved_7|>": 32022,
|
59 |
+
"<|reserved_8|>": 32023,
|
60 |
+
"<|reserved_9|>": 32024,
|
61 |
+
"<|start_header_id|>": 32012,
|
62 |
+
"<|system|>": 32009,
|
63 |
+
"<|user|>": 32008,
|
64 |
+
"[/INST]": 32005,
|
65 |
+
"[INST]": 32004
|
66 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"max_position_embeddings": 16384,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 4,
|
18 |
+
"pad_token_id": 32001,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.38.0",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32064
|
28 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 3131772928
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
161 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
162 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
163 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
164 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
165 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
166 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
167 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
168 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
169 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
170 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
171 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
172 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
173 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
174 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
175 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
176 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
177 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
178 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
179 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
180 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
181 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
182 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
183 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
184 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
185 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
186 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
187 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
188 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
189 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
190 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
191 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
192 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
193 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
194 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
195 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
196 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
197 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
198 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
199 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
200 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
201 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
202 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
203 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
204 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
205 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
206 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
207 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
208 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
209 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
210 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
211 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
212 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
213 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
214 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
215 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
216 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
217 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
218 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
219 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
220 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
221 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
222 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
223 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
224 |
+
"model.norm.weight": "model.safetensors"
|
225 |
+
}
|
226 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|im_start|>",
|
5 |
+
"</s>",
|
6 |
+
"[INST]",
|
7 |
+
"[/INST]",
|
8 |
+
"<<SYS>>",
|
9 |
+
"<</SYS>>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|system|>",
|
12 |
+
"<|assistant|>",
|
13 |
+
"<|begin_of_text|>",
|
14 |
+
"<|start_header_id|>",
|
15 |
+
"<|end_header_id|>",
|
16 |
+
"<|eot_id|>",
|
17 |
+
"<|reserved_0|>",
|
18 |
+
"<|reserved_1|>",
|
19 |
+
"<|reserved_2|>",
|
20 |
+
"<|reserved_3|>",
|
21 |
+
"<|reserved_4|>",
|
22 |
+
"<|reserved_5|>",
|
23 |
+
"<|reserved_6|>",
|
24 |
+
"<|reserved_7|>",
|
25 |
+
"<|reserved_8|>",
|
26 |
+
"<|reserved_9|>",
|
27 |
+
"<|reserved_10|>",
|
28 |
+
"<|reserved_11|>",
|
29 |
+
"<|reserved_12|>",
|
30 |
+
"<|reserved_13|>",
|
31 |
+
"<|reserved_14|>",
|
32 |
+
"<|reserved_15|>",
|
33 |
+
"<|reserved_16|>",
|
34 |
+
"<|reserved_17|>",
|
35 |
+
"<|reserved_18|>",
|
36 |
+
"<|reserved_19|>",
|
37 |
+
"<|reserved_20|>",
|
38 |
+
"<|reserved_21|>",
|
39 |
+
"<|reserved_22|>",
|
40 |
+
"<|reserved_23|>",
|
41 |
+
"<|reserved_24|>",
|
42 |
+
"<|reserved_25|>",
|
43 |
+
"<|reserved_26|>",
|
44 |
+
"<|reserved_27|>",
|
45 |
+
"<|reserved_28|>",
|
46 |
+
"<|reserved_29|>",
|
47 |
+
"<|reserved_30|>",
|
48 |
+
"<|reserved_31|>",
|
49 |
+
"<|reserved_32|>",
|
50 |
+
"<|reserved_33|>",
|
51 |
+
"<|reserved_34|>",
|
52 |
+
"<|reserved_35|>",
|
53 |
+
"<|reserved_36|>",
|
54 |
+
"<|reserved_37|>",
|
55 |
+
"<|reserved_38|>",
|
56 |
+
"<|reserved_39|>",
|
57 |
+
"<|reserved_40|>",
|
58 |
+
"<|reserved_41|>",
|
59 |
+
"<|reserved_42|>",
|
60 |
+
"<|reserved_43|>",
|
61 |
+
"<|reserved_44|>",
|
62 |
+
"<|reserved_45|>",
|
63 |
+
"<|reserved_46|>",
|
64 |
+
"<|reserved_47|>",
|
65 |
+
"<|reserved_48|>"
|
66 |
+
],
|
67 |
+
"bos_token": {
|
68 |
+
"content": "<s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"eos_token": {
|
75 |
+
"content": "<|im_end|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"pad_token": {
|
82 |
+
"content": "<|pad|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"unk_token": {
|
89 |
+
"content": "<unk>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
}
|
95 |
+
}
|
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 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|end_of_turn|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|pad|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|im_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "[INST]",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "[/INST]",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<<SYS>>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<</SYS>>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|user|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|system|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|assistant|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|begin_of_text|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|start_header_id|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|end_header_id|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|eot_id|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|reserved_0|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|reserved_1|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|reserved_2|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|reserved_3|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|reserved_4|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|reserved_5|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|reserved_6|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|reserved_7|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|reserved_8|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|reserved_9|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|reserved_10|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|reserved_11|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|reserved_12|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|reserved_13|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|reserved_14|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|reserved_15|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|reserved_16|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|reserved_17|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|reserved_18|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|reserved_19|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|reserved_20|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|reserved_21|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|reserved_22|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|reserved_23|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|reserved_24|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|reserved_25|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|reserved_26|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|reserved_27|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|reserved_28|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|reserved_29|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|reserved_30|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|reserved_31|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|reserved_32|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|reserved_33|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|reserved_34|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|reserved_35|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|reserved_36|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|reserved_37|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|reserved_38|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|reserved_39|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|reserved_40|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|reserved_41|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|reserved_42|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|reserved_43|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|reserved_44|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|reserved_45|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|reserved_46|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|reserved_47|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|reserved_48|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
}
|
542 |
+
},
|
543 |
+
"additional_special_tokens": [
|
544 |
+
"<|end_of_turn|>",
|
545 |
+
"<|im_start|>",
|
546 |
+
"</s>",
|
547 |
+
"[INST]",
|
548 |
+
"[/INST]",
|
549 |
+
"<<SYS>>",
|
550 |
+
"<</SYS>>",
|
551 |
+
"<|user|>",
|
552 |
+
"<|system|>",
|
553 |
+
"<|assistant|>",
|
554 |
+
"<|begin_of_text|>",
|
555 |
+
"<|start_header_id|>",
|
556 |
+
"<|end_header_id|>",
|
557 |
+
"<|eot_id|>",
|
558 |
+
"<|reserved_0|>",
|
559 |
+
"<|reserved_1|>",
|
560 |
+
"<|reserved_2|>",
|
561 |
+
"<|reserved_3|>",
|
562 |
+
"<|reserved_4|>",
|
563 |
+
"<|reserved_5|>",
|
564 |
+
"<|reserved_6|>",
|
565 |
+
"<|reserved_7|>",
|
566 |
+
"<|reserved_8|>",
|
567 |
+
"<|reserved_9|>",
|
568 |
+
"<|reserved_10|>",
|
569 |
+
"<|reserved_11|>",
|
570 |
+
"<|reserved_12|>",
|
571 |
+
"<|reserved_13|>",
|
572 |
+
"<|reserved_14|>",
|
573 |
+
"<|reserved_15|>",
|
574 |
+
"<|reserved_16|>",
|
575 |
+
"<|reserved_17|>",
|
576 |
+
"<|reserved_18|>",
|
577 |
+
"<|reserved_19|>",
|
578 |
+
"<|reserved_20|>",
|
579 |
+
"<|reserved_21|>",
|
580 |
+
"<|reserved_22|>",
|
581 |
+
"<|reserved_23|>",
|
582 |
+
"<|reserved_24|>",
|
583 |
+
"<|reserved_25|>",
|
584 |
+
"<|reserved_26|>",
|
585 |
+
"<|reserved_27|>",
|
586 |
+
"<|reserved_28|>",
|
587 |
+
"<|reserved_29|>",
|
588 |
+
"<|reserved_30|>",
|
589 |
+
"<|reserved_31|>",
|
590 |
+
"<|reserved_32|>",
|
591 |
+
"<|reserved_33|>",
|
592 |
+
"<|reserved_34|>",
|
593 |
+
"<|reserved_35|>",
|
594 |
+
"<|reserved_36|>",
|
595 |
+
"<|reserved_37|>",
|
596 |
+
"<|reserved_38|>",
|
597 |
+
"<|reserved_39|>",
|
598 |
+
"<|reserved_40|>",
|
599 |
+
"<|reserved_41|>",
|
600 |
+
"<|reserved_42|>",
|
601 |
+
"<|reserved_43|>",
|
602 |
+
"<|reserved_44|>",
|
603 |
+
"<|reserved_45|>",
|
604 |
+
"<|reserved_46|>",
|
605 |
+
"<|reserved_47|>",
|
606 |
+
"<|reserved_48|>"
|
607 |
+
],
|
608 |
+
"bos_token": "<s>",
|
609 |
+
"chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
|
610 |
+
"clean_up_tokenization_spaces": false,
|
611 |
+
"eos_token": "<|im_end|>",
|
612 |
+
"kwargs": {
|
613 |
+
"eos_token": "<|im_end|>",
|
614 |
+
"pad_token": "<|pad|>",
|
615 |
+
"padding_side": "right"
|
616 |
+
},
|
617 |
+
"legacy": true,
|
618 |
+
"model_max_length": 1000000000000000019884624838656,
|
619 |
+
"pad_token": "<|pad|>",
|
620 |
+
"padding_side": "right",
|
621 |
+
"tokenizer_class": "LlamaTokenizer",
|
622 |
+
"unk_token": "<unk>",
|
623 |
+
"use_default_system_prompt": false
|
624 |
+
}
|