saucam commited on
Commit
e599b69
1 Parent(s): 3a2e88c

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - Phind/Phind-CodeLlama-34B-v2
7
+ - codefuse-ai/CodeFuse-CodeLlama-34B
8
+ base_model:
9
+ - Phind/Phind-CodeLlama-34B-v2
10
+ - codefuse-ai/CodeFuse-CodeLlama-34B
11
+ ---
12
+
13
+ # Phind-Codefuse-34B
14
+
15
+ Phind-Codefuse-34B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [Phind/Phind-CodeLlama-34B-v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2)
17
+ * [codefuse-ai/CodeFuse-CodeLlama-34B](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: Phind/Phind-CodeLlama-34B-v2
24
+ parameters:
25
+ density: 0.5
26
+ weight: 0.6
27
+ # No parameters necessary for base model
28
+ - model: codefuse-ai/CodeFuse-CodeLlama-34B
29
+ parameters:
30
+ density: 0.5
31
+ weight: 0.4
32
+ merge_method: task_arithmetic
33
+ base_model: Phind/Phind-CodeLlama-34B-v2
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 = "saucam/Phind-Codefuse-34B"
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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Phind/Phind-CodeLlama-34B-v2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 22016,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: Phind/Phind-CodeLlama-34B-v2
3
+ parameters:
4
+ density: 0.5
5
+ weight: 0.6
6
+ # No parameters necessary for base model
7
+ - model: codefuse-ai/CodeFuse-CodeLlama-34B
8
+ parameters:
9
+ density: 0.5
10
+ weight: 0.4
11
+ merge_method: task_arithmetic
12
+ base_model: Phind/Phind-CodeLlama-34B-v2
13
+ parameters:
14
+ int8_mask: true
15
+ dtype: bfloat16
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9955c86130f4fbe64191559036472991575147ba5ff0e2aa3887ad47f755ea4
3
+ size 9852623784
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246f4cd4a801cbc917507883b58254b9f339a3a5234f8e199a00bf75468c9214
3
+ size 9689078960
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc0e485e996ca2ba1e79340c313d2407d1a6f866e541cb6203879bf7f1ff48e
3
+ size 9689078992
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b468039ead1820ac95048446bd3401ff206c84f72b1d15752380b75646c670fa
3
+ size 9689078992
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a131681fa71ba4c8da731f072129243772c7efb3d0a8a11f5640139c59edebf
3
+ size 9689078992
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7365e98911d412d1b01798dfb32c9abb865756a7fe39a7c49c5d0482084b009f
3
+ size 9689078992
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a788dbe73bebbd7c1eea5f585ccc215c1838d8c8d71d71aaf3bf4071882386
3
+ size 9189972688
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-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.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
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": true,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 4096,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }