powermove72 commited on
Commit
38ab56e
1 Parent(s): f604c6b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - powermove72/Shark-1
4
+ - eren23/OGNO-7b-dpo-truthful
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - powermove72/Shark-1
10
+ - eren23/OGNO-7b-dpo-truthful
11
+ ---
12
+
13
+ # Shark-1-Ogno-9b-passthrough
14
+
15
+ Shark-1-Ogno-9b-passthrough is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [powermove72/Shark-1](https://huggingface.co/powermove72/Shark-1)
17
+ * [eren23/OGNO-7b-dpo-truthful](https://huggingface.co/eren23/OGNO-7b-dpo-truthful)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: powermove72/Shark-1
25
+ layer_range: [0, 16]
26
+ - sources:
27
+ - model: eren23/OGNO-7b-dpo-truthful
28
+ layer_range: [8, 32]
29
+ merge_method: passthrough
30
+ tokenizer_source: union
31
+ dtype: float16
32
+ ```
33
+
34
+ ## 💻 Usage
35
+
36
+ ```python
37
+ !pip install -qU transformers accelerate
38
+
39
+ from transformers import AutoTokenizer
40
+ import transformers
41
+ import torch
42
+
43
+ model = "powermove72/Shark-1-Ogno-9b-passthrough"
44
+ messages = [{"role": "user", "content": "What is a large language model?"}]
45
+
46
+ tokenizer = AutoTokenizer.from_pretrained(model)
47
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
48
+ pipeline = transformers.pipeline(
49
+ "text-generation",
50
+ model=model,
51
+ torch_dtype=torch.float16,
52
+ device_map="auto",
53
+ )
54
+
55
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
56
+ print(outputs[0]["generated_text"])
57
+ ```
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "powermove72/Shark-1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModel": "GritLM/GritLM-7B--modeling_gritlm7b.MistralModel",
9
+ "AutoModelForCausalLM": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForCausalLM",
10
+ "AutoModelForSequenceClassification": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForSequenceClassification"
11
+ },
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 14336,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "max_position_embeddings": 32768,
25
+ "model_type": "mistral",
26
+ "num_attention_heads": 32,
27
+ "num_hidden_layers": 40,
28
+ "num_key_value_heads": 8,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000.0,
31
+ "sliding_window": 4096,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.41.2",
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: powermove72/Shark-1
5
+ layer_range: [0, 16]
6
+ - sources:
7
+ - model: eren23/OGNO-7b-dpo-truthful
8
+ layer_range: [8, 32]
9
+ merge_method: passthrough
10
+ tokenizer_source: union
11
+ dtype: float16
12
+
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f06f6eacc9de7700783ff69f6a9a46ea126d9ada7cc510b67d4e0e48474211b
3
+ size 960521544
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1373d4c8bf37e1c1be4badd4836f9150015774c0f06d5792a8f9195209c8cc04
3
+ size 905995856
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ea49210b5ca569b434bf6b3b1cb7846c0c169a377b031308b25d32cc7fd1b4
3
+ size 989890704
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bd6ae265fb6bfe2840a9622311463f0a812a5b6d5d41fc2b0cf8a615aedc03
3
+ size 998296048
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54de4571b9189465b608d1174ee624fc413394ffa2ef8ff0fcbb12b2b74b010e
3
+ size 981502432
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154bd31843aa8e94115183d8c2c1fde7dccff31ef83a0d4b3a8d32371783a424
3
+ size 922798672
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6b28cdd048c1315c9313fb55ad83f18067ea8b32f69104397789a34719f83c
3
+ size 989882408
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e4a84e100124d1dc8799e76734bde0e667539b9f63feb3001772691a90937f
3
+ size 989890712
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e62e50025622ab5baca7c2e0b3c3374012f3e725feea034f0bcf5d90270303
3
+ size 998287720
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ed048d74c6ad7e79508cf26819c4c86a85c742b16bbc966a56ed3b32937970
3
+ size 947956192
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7edb8d1ab03a819b9092569aba87ec51e5b462e84fbb34fa196cf5e37c0527c
3
+ size 989890712
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8586ee47786839eae7a33ec9dae3ce7bdbf58a997fa3a53a8e3409535a0d61c
3
+ size 989890712
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f4a9ced01c2bb44d3581ff36500f4e1e5d6f165b98ca27f6a0b1ea9f3bddb9
3
+ size 998287736
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ee07f5dee05dbe4f645a73528784408fe5b5038b2166b12180e59a6d07d4ff
3
+ size 947956184
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d29836beb74b72d1dbb09176c536e89a95dccd820280912311d5a902100a69
3
+ size 989890704
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4a1365e88479ecbf8140801608dcabd3303e42e5d2ae1db70720f0ad5fffbc
3
+ size 989890688
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e5b3cf81d0b4ef5095f58dc86af2647e7fd69763c29939996bbd2d1620ca0e
3
+ size 989898984
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e3bf0185f8ef99f7708521176e4b7e8ca5d63e2aa992eefbc4dc5f57a7b998
3
+ size 989890696
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768e9761c629320afd7c77258b8301310838654d8decbe4de8a0cfa47ddc6dd6
3
+ size 402679256
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 17973256192}, "weight_map": {"lm_head.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "max_length": 2048,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_to_multiple_of": null,
39
+ "pad_token": "<s>",
40
+ "pad_token_type_id": 0,
41
+ "padding_side": "right",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "stride": 0,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "truncation_side": "right",
47
+ "truncation_strategy": "longest_first",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }