Badgids commited on
Commit
710a342
1 Parent(s): 0cde54c
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. Gonzo-Chat-7B-Q4_K_M.gguf +3 -0
  3. README.md +52 -1
  4. config.json +26 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Gonzo-Chat-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Gonzo-Chat-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6eb3cd62f932af310ef8eea9fb1297f009969d2d772efa90ea0d1a5c7601532
3
+ size 4523063008
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - Nondzu/Mistral-7B-Instruct-v0.2-code-ft
4
+ - NousResearch/Nous-Hermes-2-Mistral-7B-DPO
5
+ - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
6
+ - eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
7
+ library_name: transformers
8
+ tags:
9
+ - mergekit
10
+ - merge
11
+
12
  ---
13
+ # Gonzo-Chat-7B
14
+
15
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
+
17
+ ## Merge Details
18
+ ### Merge Method
19
+
20
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO) as a base.
21
+
22
+ ### Models Merged
23
+
24
+ The following models were included in the merge:
25
+ * [Nondzu/Mistral-7B-Instruct-v0.2-code-ft](https://huggingface.co/Nondzu/Mistral-7B-Instruct-v0.2-code-ft)
26
+ * [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)
27
+ * [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
28
+
29
+ ### Configuration
30
+
31
+ The following YAML configuration was used to produce this model:
32
+
33
+ ```yaml
34
+ models:
35
+ - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
36
+ # No parameters necessary for base model
37
+ - model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
38
+ parameters:
39
+ density: 0.53
40
+ weight: 0.4
41
+ - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
42
+ parameters:
43
+ density: 0.53
44
+ weight: 0.3
45
+ - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
46
+ parameters:
47
+ density: 0.53
48
+ weight: 0.3
49
+ merge_method: dare_ties
50
+ base_model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
51
+ parameters:
52
+ int8_mask: true
53
+ dtype: bfloat16
54
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Gonzo-Chat-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": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }