Upload 20 files
Browse files- README.md +45 -0
- config.json +26 -0
- maid (1).jpeg +0 -0
- mergekit_config.yml +13 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- mistralai/Mistral-7B-Instruct-v0.2
|
4 |
+
- Nexusflow/Starling-LM-7B-beta
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# sfM-v1
|
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 passthrough merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
24 |
+
* [Nexusflow/Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta)
|
25 |
+
* fM-v2
|
26 |
+
|
27 |
+
### Configuration
|
28 |
+
|
29 |
+
The following YAML configuration was used to produce this model:
|
30 |
+
|
31 |
+
```yaml
|
32 |
+
slices:
|
33 |
+
- sources:
|
34 |
+
- model: "fM-v2"
|
35 |
+
layer_range: [0, 16]
|
36 |
+
- sources:
|
37 |
+
- model: "Nexusflow/Starling-LM-7B-beta"
|
38 |
+
layer_range: [8, 24]
|
39 |
+
- sources:
|
40 |
+
- model: "mistralai/Mistral-7B-Instruct-v0.2"
|
41 |
+
layer_range: [17, 32]
|
42 |
+
merge_method: passthrough
|
43 |
+
dtype: float16
|
44 |
+
name: fM-v2
|
45 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 47,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
maid (1).jpeg
ADDED
mergekit_config.yml
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: "fM-v2"
|
4 |
+
layer_range: [0, 16]
|
5 |
+
- sources:
|
6 |
+
- model: "Nexusflow/Starling-LM-7B-beta"
|
7 |
+
layer_range: [8, 24]
|
8 |
+
- sources:
|
9 |
+
- model: "mistralai/Mistral-7B-Instruct-v0.2"
|
10 |
+
layer_range: [17, 32]
|
11 |
+
merge_method: passthrough
|
12 |
+
dtype: float16
|
13 |
+
name: fM-v2
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ca43cf5169d47d21cc5183c3534558b6f2dc01c96b1801df6f3afe4788338f9
|
3 |
+
size 1946210712
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8afb16b5292d02fa95019b740e8f0126836e2cbfe9c3b81e6d079c025099893d
|
3 |
+
size 1979773096
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580743b622a5929e8ba76768b2d7a19d0894b53666dedb69375fd3afde854bea
|
3 |
+
size 1996567648
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab206dec336da21aa33e172d63f59661911ef1543e01f2c815f323f5cc24cedd
|
3 |
+
size 1895903640
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:656a8283d5b297b1f2d337f6a4a5c397fa499e4d3c1023b8b6bd28c47a8dc757
|
3 |
+
size 1979789736
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03f31690bf6d8d9220c7902512fc18e17f8854c5c20001f635548fe713a1b82c
|
3 |
+
size 1996584208
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd06b8f7092c813bb6ad7d29ed403b3a59720b9cee6d5c11670ccc93206ed587
|
3 |
+
size 1956712232
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e046a713e8b55b350554a21b0aaf9f46348324b69907aaf13813a19d68cc2bc
|
3 |
+
size 1946243944
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0de7b34d5e7b4e1db90ca3bddc4efe4a11c0481798e67c1a2c86a18546af6a7e
|
3 |
+
size 1895894880
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39123f813c7b3d049648e079c88de9611da983e501aba7510384bda917016bf0
|
3 |
+
size 1973498016
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cf234d9240bb0d50ffce59c8ab5531db44e7234c69cdcccaf76ccc680a3f502
|
3 |
+
size 1459695200
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "lm_head.weight": "model-00007-of-00011.safetensors", "model.norm.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.embed_tokens.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
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.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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": null,
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|