powermove72 commited on
Commit
6886ec8
1 Parent(s): 067266f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - powermove72/Shark-1
4
+ - S-miguel/The-Trinity-Coder-7B
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - powermove72/Shark-1
10
+ - S-miguel/The-Trinity-Coder-7B
11
+ ---
12
+
13
+ # Shark-Coder-9b
14
+
15
+ Shark-Coder-9b 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
+ * [S-miguel/The-Trinity-Coder-7B](https://huggingface.co/S-miguel/The-Trinity-Coder-7B)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: powermove72/Shark-1
25
+ layer_range: [0, 16]
26
+ - sources:
27
+ - model: S-miguel/The-Trinity-Coder-7B
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-Coder-9b"
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "S-miguel/The-Trinity-Coder-7B",
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": "float16",
23
+ "transformers_version": "4.42.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
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: S-miguel/The-Trinity-Coder-7B
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 sha256:5964ed128fe2d157dacd87dfcc3582b7fa2402aed5c55015387567daa2cee1ff
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:a13404d748861846eb6a14e2984ec4e27c6ca56d04d7ba874636b96267a9a88a
3
+ size 905995856
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c7c81296906c65c862cf88e2dd30315712e8cd3a0e2081ceb8d91c2388b338
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:ff6147b404697e3a2b08848a5bffca708f8dd8d935d9f4e594e9634828df8f4a
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:a2e3889fbb13fc0b64da698b296a829264dd565a6095c9a51106b15f6c0b390f
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:ee51c129c9db454e8ebd91c275a9096d9c893c1ed5fa3f80b728666486faa928
3
+ size 922798672
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a85be94c45ecebfd63178f6431b9d1b9e57cfc81d543671b457e0da3a3140c3
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:b39fae68f7a131fa3cdcc0bea67172833756ab029e5b09fe4ab135614f7a1fdd
3
+ size 989890712
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748d31015aea277a90fa8de3b674a915c60fa39256d7d250bb5322510a421e0e
3
+ size 998287720
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a4e5d937ecfb55d913ee3bfebac35520aa2c8f3af8bebf1d134beb6de29265
3
+ size 947956192
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186fc61ad61e60edf42679e6b3fe248127e68df668f115fb013c38e516bb266d
3
+ size 989890712
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f35efdea3eb05da73ceb89fba8d37942538a66a930f17cd519dc7d8718502d1
3
+ size 989890712
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d10456e7485babd4bfac1805ee84a9ecc07ab10ce439e9d5aff010a6974008
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:b9f44d37a400dada6010efa095acb306b29d0d7714b43b3af02fdd78684f76b9
3
+ size 947956184
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad5fdf606626f1caff4a72b60603da967f4ac2641bdee4b09ad30378ba5b97b
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 sha256:94b063e8d6bfff1e0cc3a46f3b48bdf3e7ae69578182587f8aad7e8f2dca82cf
3
+ size 989898984
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7a89214630cbd2f02c2e9ac4a9f1489d5fee7cd3103d17d9d3e624a039ed2a
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:a0d7061a0b03f014c5f38e896ac6b55f151af3b1ac9ab70eac4d04f05301be1e
3
+ size 402679256
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
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
+ }