Upload folder using huggingface_hub
Browse files- README.md +30 -0
- config.json +26 -0
- mergekit_config.yml +11 -0
- model-00001-of-00010.safetensors +3 -0
- model-00002-of-00010.safetensors +3 -0
- model-00003-of-00010.safetensors +3 -0
- model-00004-of-00010.safetensors +3 -0
- model-00005-of-00010.safetensors +3 -0
- model-00006-of-00010.safetensors +3 -0
- model-00007-of-00010.safetensors +3 -0
- model-00008-of-00010.safetensors +3 -0
- model-00009-of-00010.safetensors +3 -0
- model-00010-of-00010.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 +40 -0
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- OpenPipe/mistral-ft-optimized-1218
|
8 |
+
- mlabonne/NeuralHermes-2.5-Mistral-7B
|
9 |
+
---
|
10 |
+
|
11 |
+
# koala-7B-slerp
|
12 |
+
|
13 |
+
koala-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
|
15 |
+
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
slices:
|
21 |
+
- sources:
|
22 |
+
- model: OpenPipe/mistral-ft-optimized-1218
|
23 |
+
layer_range: [0, 32]
|
24 |
+
- sources:
|
25 |
+
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
|
26 |
+
layer_range: [24, 32]
|
27 |
+
merge_method: passthrough
|
28 |
+
dtype: bfloat16
|
29 |
+
|
30 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "OpenPipe/mistral-ft-optimized-1218",
|
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": 40,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.35.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: OpenPipe/mistral-ft-optimized-1218
|
5 |
+
layer_range: [0, 32]
|
6 |
+
- sources:
|
7 |
+
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
|
8 |
+
layer_range: [24, 32]
|
9 |
+
merge_method: passthrough
|
10 |
+
dtype: bfloat16
|
11 |
+
|
model-00001-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:485db8045963e8b1f8c875b9fa18633834986d8997a5ce7900bc2bf1a19a0bcc
|
3 |
+
size 1998655576
|
model-00002-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ccae12d53b4acd52e58742f93c0963d0d823719671f2ca7e359aa1e54a1dee8
|
3 |
+
size 1988178472
|
model-00003-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49f237d2ac4c0d84d767abd58d75d7064e24c74cea9c47201a2809480544241
|
3 |
+
size 1946243984
|
model-00004-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aee09f6aa66da342ddc8894e69c229e017c400e6222b75ca0a5f4ee1b7151b3c
|
3 |
+
size 1946227352
|
model-00005-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a8a0a8759c2562ffe26924b794564190e27867f660b34b18d3e82ab480349e
|
3 |
+
size 1988178456
|
model-00006-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67a93cbe6f6d41b56ccc19a0384617110b3da269df46a6fd122f68fdcae5201c
|
3 |
+
size 1971401024
|
model-00007-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af5c9da0c4dbeb33769205461f8cbd335a8388e53647f7c516aee6f73dcf549
|
3 |
+
size 1946243992
|
model-00008-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4b2d6f65571be25a8dd9499871d5d79938200a8481c1807bab07f55b863a103
|
3 |
+
size 1998663664
|
model-00009-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:429494d60b2e492367e930b0a2b6c1abe6dec26c0dea9b1faa7054716fa55f34
|
3 |
+
size 1988178472
|
model-00010-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32db3c6f53d75f10cb90389c25796a4c9caceb828e57f8b4e5949422ffdf770e
|
3 |
+
size 201343792
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "lm_head.weight": "model-00008-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.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 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": true,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": null,
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"spaces_between_special_tokens": false,
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|