louisbrulenaudet commited on
Commit
082c97c
β€’
1 Parent(s): 39b1ddb

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - deepseek-ai/deepseek-coder-6.7b-instruct
7
+ - defog/sqlcoder-7b-2
8
+ base_model:
9
+ - deepseek-ai/deepseek-coder-6.7b-instruct
10
+ - defog/sqlcoder-7b-2
11
+ ---
12
+
13
+ # DevPearl-7B-dare-ties
14
+
15
+ DevPearl-7B-dare-ties is a merge of the following models :
16
+ * [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct)
17
+ * [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2)
18
+
19
+ ## Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: codellama/CodeLlama-7b-Instruct-hf
24
+ - model: deepseek-ai/deepseek-coder-6.7b-instruct
25
+ parameters:
26
+ density: 0.53
27
+ weight: 0.7
28
+ - model: defog/sqlcoder-7b-2
29
+ parameters:
30
+ density: 0.45
31
+ weight: 0.3
32
+ merge_method: dare_ties
33
+ base_model: codellama/CodeLlama-7b-Instruct-hf
34
+ parameters:
35
+ int8_mask: true
36
+ dtype: bfloat16
37
+ ```
38
+
39
+ ## Usage
40
+
41
+ ```python
42
+ !pip install -qU transformers accelerate
43
+
44
+ from transformers import AutoTokenizer
45
+ import transformers
46
+ import torch
47
+
48
+ model = "louisbrulenaudet/DevPearl-7B-dare-ties"
49
+ messages = [{"role": "user", "content": "What is a large language model?"}]
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model)
52
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
53
+ pipeline = transformers.pipeline(
54
+ "text-generation",
55
+ model=model,
56
+ torch_dtype=torch.float16,
57
+ device_map="auto",
58
+ )
59
+
60
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
61
+ print(outputs[0]["generated_text"])
62
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
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": 11008,
13
+ "max_position_embeddings": 16384,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.35.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32016
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: codellama/CodeLlama-7b-Instruct-hf
4
+ - model: deepseek-ai/deepseek-coder-6.7b-instruct
5
+ parameters:
6
+ density: 0.53
7
+ weight: 0.7
8
+ - model: defog/sqlcoder-7b-2
9
+ parameters:
10
+ density: 0.45
11
+ weight: 0.3
12
+ merge_method: dare_ties
13
+ base_model: codellama/CodeLlama-7b-Instruct-hf
14
+ parameters:
15
+ int8_mask: true
16
+ dtype: bfloat16
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1531caee193e70cd2bdb542e6b3ba1d6785197cb37cfe532b18f3e74ffca92
3
+ size 1933644544
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab2045c4744d3806dbfa4c6e94cc31cd4125bfc109988ff7510acc55d6182006
3
+ size 1933661136
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5018b76f4882d056b86a93a30171075a4e1f1d9071d7706bdc486b1c1102edb
3
+ size 1971507280
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da0aa57f4dccc6f2a5d8cd3e720679f8b6d51d1b50b92fe017ca0cc9207becf
3
+ size 1933661192
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7941bdeca1888832896dd90b9243dbabb05bd3dad7d9d0e88e47e8b00ef1eda5
3
+ size 1933661184
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea30c24673a3621bd75b6660fe75138a24711058eab664fb600c8c06caf3987f
3
+ size 1994609056
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7618702473187b2ed5ce36cc0e10b2484d0e27b6411b632c157f4911132cc970
3
+ size 1776382728
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.embed_tokens.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00006-of-00007.safetensors", "model.norm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": true,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32007": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32008": {
36
+ "content": "▁<SUF>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32009": {
44
+ "content": "▁<MID>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32010": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "▁<PRE>",
62
+ "▁<MID>",
63
+ "▁<SUF>",
64
+ "▁<EOT>"
65
+ ],
66
+ "bos_token": "<s>",
67
+ "clean_up_tokenization_spaces": false,
68
+ "eos_token": "</s>",
69
+ "eot_token": "▁<EOT>",
70
+ "fill_token": "<FILL_ME>",
71
+ "legacy": null,
72
+ "middle_token": "▁<MID>",
73
+ "model_max_length": 1000000000000000019884624838656,
74
+ "pad_token": null,
75
+ "prefix_token": "▁<PRE>",
76
+ "sp_model_kwargs": {},
77
+ "suffix_token": "▁<SUF>",
78
+ "tokenizer_class": "CodeLlamaTokenizer",
79
+ "unk_token": "<unk>",
80
+ "use_default_system_prompt": false
81
+ }