Hugging Face's logo

Vikhrmodels
/
Vikhr-7B-instruct_0.4-GGUF

GGUF
Russian
English
llama-cpp
Inference Endpoints
imatrix
conversational
Model card Files Community
WaveCut commited on
Commit
6ae81ff
•
1 Parent(s): 9e08ac6

Upload folder using huggingface_hub

Browse files
Files changed (34) hide show
  1. .gitattributes +32 -0
  2. README.md +42 -0
  3. vikhr-7b-instruct_0.4.IQ1_M.gguf +3 -0
  4. vikhr-7b-instruct_0.4.IQ1_S.gguf +3 -0
  5. vikhr-7b-instruct_0.4.IQ2_M.gguf +3 -0
  6. vikhr-7b-instruct_0.4.IQ2_S.gguf +3 -0
  7. vikhr-7b-instruct_0.4.IQ2_XS.gguf +3 -0
  8. vikhr-7b-instruct_0.4.IQ2_XXS.gguf +3 -0
  9. vikhr-7b-instruct_0.4.IQ3_M.gguf +3 -0
  10. vikhr-7b-instruct_0.4.IQ3_S.gguf +3 -0
  11. vikhr-7b-instruct_0.4.IQ3_XS.gguf +3 -0
  12. vikhr-7b-instruct_0.4.IQ3_XXS.gguf +3 -0
  13. vikhr-7b-instruct_0.4.IQ4_NL.gguf +3 -0
  14. vikhr-7b-instruct_0.4.IQ4_XS.gguf +3 -0
  15. vikhr-7b-instruct_0.4.Q2_K.gguf +3 -0
  16. vikhr-7b-instruct_0.4.Q2_K_S.gguf +3 -0
  17. vikhr-7b-instruct_0.4.Q3_K.gguf +3 -0
  18. vikhr-7b-instruct_0.4.Q3_K_L.gguf +3 -0
  19. vikhr-7b-instruct_0.4.Q3_K_M.gguf +3 -0
  20. vikhr-7b-instruct_0.4.Q3_K_S.gguf +3 -0
  21. vikhr-7b-instruct_0.4.Q4_0.gguf +3 -0
  22. vikhr-7b-instruct_0.4.Q4_1.gguf +3 -0
  23. vikhr-7b-instruct_0.4.Q4_K.gguf +3 -0
  24. vikhr-7b-instruct_0.4.Q4_K_M.gguf +3 -0
  25. vikhr-7b-instruct_0.4.Q4_K_S.gguf +3 -0
  26. vikhr-7b-instruct_0.4.Q5_0.gguf +3 -0
  27. vikhr-7b-instruct_0.4.Q5_1.gguf +3 -0
  28. vikhr-7b-instruct_0.4.Q5_K.gguf +3 -0
  29. vikhr-7b-instruct_0.4.Q5_K_M.gguf +3 -0
  30. vikhr-7b-instruct_0.4.Q5_K_S.gguf +3 -0
  31. vikhr-7b-instruct_0.4.Q6_K.gguf +3 -0
  32. vikhr-7b-instruct_0.4.Q8_0.gguf +3 -0
  33. vikhr-7b-instruct_0.4.fp16.gguf +3 -0
  34. vikhr-7b-instruct_0.4.fp16.gguf.Imatrix.dat +3 -0
.gitattributes CHANGED
@@ -33,3 +33,35 @@ 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
+ vikhr-7b-instruct_0.4.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ vikhr-7b-instruct_0.4.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ vikhr-7b-instruct_0.4.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ vikhr-7b-instruct_0.4.IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ vikhr-7b-instruct_0.4.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ vikhr-7b-instruct_0.4.IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ vikhr-7b-instruct_0.4.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ vikhr-7b-instruct_0.4.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ vikhr-7b-instruct_0.4.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
45
+ vikhr-7b-instruct_0.4.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
46
+ vikhr-7b-instruct_0.4.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
47
+ vikhr-7b-instruct_0.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
48
+ vikhr-7b-instruct_0.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
49
+ vikhr-7b-instruct_0.4.Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ vikhr-7b-instruct_0.4.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ vikhr-7b-instruct_0.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
52
+ vikhr-7b-instruct_0.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
53
+ vikhr-7b-instruct_0.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
54
+ vikhr-7b-instruct_0.4.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
55
+ vikhr-7b-instruct_0.4.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
56
+ vikhr-7b-instruct_0.4.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
57
+ vikhr-7b-instruct_0.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
58
+ vikhr-7b-instruct_0.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
59
+ vikhr-7b-instruct_0.4.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
60
+ vikhr-7b-instruct_0.4.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
61
+ vikhr-7b-instruct_0.4.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
62
+ vikhr-7b-instruct_0.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
63
+ vikhr-7b-instruct_0.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
64
+ vikhr-7b-instruct_0.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
65
+ vikhr-7b-instruct_0.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
66
+ vikhr-7b-instruct_0.4.fp16.gguf filter=lfs diff=lfs merge=lfs -text
67
+ vikhr-7b-instruct_0.4.fp16.gguf.Imatrix.dat filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Релиз вихря 0.3-0.4
7
+
8
+ Долили сильно больше данных в sft, теперь стабильнее работает json и multiturn, слегка подточили параметры претрена модели
9
+
10
+ [collab](https://colab.research.google.com/drive/15O9LwZhVUa1LWhZa2UKr_B-KOKenJBvv#scrollTo=5EeNFU2-9ERi)
11
+
12
+ ```python
13
+
14
+
15
+ from transformers import AutoTokenizer, AutoModelForCausalLM
16
+ import torch
17
+ model = AutoModelForCausalLM.from_pretrained("AlexWortega/v5-it",
18
+ device_map="auto",
19
+ attn_implementation="flash_attention_2",
20
+ torch_dtype=torch.bfloat16)
21
+
22
+ tokenizer = AutoTokenizer.from_pretrained("AlexWortega/v5-it")
23
+ from transformers import AutoTokenizer, pipeline
24
+ pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
25
+ prompts = [
26
+ "В чем разница между фруктом и овощем?",
27
+ "Годы жизни колмагорова?"]
28
+
29
+ def test_inference(prompt):
30
+ prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
31
+ print(prompt)
32
+ outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
33
+ return outputs[0]['generated_text'][len(prompt):].strip()
34
+
35
+
36
+ for prompt in prompts:
37
+ print(f" prompt:\n{prompt}")
38
+ print(f" response:\n{test_inference(prompt)}")
39
+ print("-"*50)
40
+
41
+ ```
42
+
vikhr-7b-instruct_0.4.IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4bcb037eaea418bf1827c9eb74be4efe9e9690ed2f7b3be861c794ea99f20d
3
+ size 1951850848
vikhr-7b-instruct_0.4.IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7967add80bb88683bbf7560f321cb76263068ceeef1fd5860b038cecc3e52738
3
+ size 1809506656
vikhr-7b-instruct_0.4.IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb79330a025228fe6324ef592758855a21fea8fe0bee9c3feda5fbf71346aa5
3
+ size 2717710656
vikhr-7b-instruct_0.4.IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7968fe14a3f883b0d276c6e4e587744849eed1e1e199206508796b993babc28d
3
+ size 2527918400
vikhr-7b-instruct_0.4.IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abac559f5558ad101e712f3e7e5097ca95826125ed3711353daea225a74dd6b9
3
+ size 2395660640
vikhr-7b-instruct_0.4.IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6ad84d4f4c0f753544f89ccf1d60106bff037a25603160a7907fd0b464f784
3
+ size 2189091168
vikhr-7b-instruct_0.4.IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4868ab3572898f1e26831fda86bca4efb00ed672dece0fab0790fd86fe06aee
3
+ size 3527511712
vikhr-7b-instruct_0.4.IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9574c959f01e328ed09d1248787ac48ef5d1dfdb499ace2bab4c2dc79aa705f
3
+ size 3425013408
vikhr-7b-instruct_0.4.IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73007b17b041cbea9324f963144fbdbe7da0d59fc8613d342de04a6654824b50
3
+ size 3261435552
vikhr-7b-instruct_0.4.IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cf999bb5cf6dfb73f9d114e2df1f798f89606e4c2637085f0648c905c4f5f1
3
+ size 3044342080
vikhr-7b-instruct_0.4.IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55afa7f770ee1548686ccc6901f05e26da1364f3aa46070fdbb40ce81435104
3
+ size 4393935872
vikhr-7b-instruct_0.4.IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2978039e1f8957346ce1cc9ac510686d7cccc904744036cebb5ad20cccb5db50
3
+ size 4169901696
vikhr-7b-instruct_0.4.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263f4cb8938d239edbb24d7568b4a0abc768c70a5e8a7c755d1238e6213079cb
3
+ size 2942269120
vikhr-7b-instruct_0.4.Q2_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61440169c30e1403678373a3acea7fcb554f26676d18d48e7824f42ae863581b
3
+ size 2751952576
vikhr-7b-instruct_0.4.Q3_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bd8eae5dde676819a0df8e87af2b88962a996a0f57f9cf25d1459d1bd905fc
3
+ size 3761606304
vikhr-7b-instruct_0.4.Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d4a285735c9b8a72c03e6281047e6a01d3828430c33d42cbf41c375071371b
3
+ size 4064644768
vikhr-7b-instruct_0.4.Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bd8eae5dde676819a0df8e87af2b88962a996a0f57f9cf25d1459d1bd905fc
3
+ size 3761606304
vikhr-7b-instruct_0.4.Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1ad3f91317f20107f0ee4f1036f693010af43facbe14abfc9385bcef0aaa52
3
+ size 3407187616
vikhr-7b-instruct_0.4.Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9d2545175c7dab1d503e540c54c86629f862b1cdafdb28895c971cec9158cc
3
+ size 4391838720
vikhr-7b-instruct_0.4.Q4_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad51abaaead1429608e5a0754fa9dbeb71ef7f5566deee80498090636ca75398
3
+ size 4833615616
vikhr-7b-instruct_0.4.Q4_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb1c20ff6eec6d3207871a320e69b946354dcf820020e91f684a18178a5264f
3
+ size 4636681216
vikhr-7b-instruct_0.4.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb1c20ff6eec6d3207871a320e69b946354dcf820020e91f684a18178a5264f
3
+ size 4636681216
vikhr-7b-instruct_0.4.Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b71fade10f2ef7cfe3ac9f7b8a0778669c0400f662675209bf7a60ef3534f2
3
+ size 4408615936
vikhr-7b-instruct_0.4.Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed2f6c9e72601abd08582909a2c52551d16252933289515bc3772208b8c4159
3
+ size 5304752640
vikhr-7b-instruct_0.4.Q5_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de40016a19207b0c8198ffcfcd99058a94571aeef5d23ac74279c8ea3370e5d0
3
+ size 5746529536
vikhr-7b-instruct_0.4.Q5_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5762c627bc2093b4b3684513ff338ad41aec67c84449414e06da6074355b99e2
3
+ size 5423766016
vikhr-7b-instruct_0.4.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5762c627bc2093b4b3684513ff338ad41aec67c84449414e06da6074355b99e2
3
+ size 5423766016
vikhr-7b-instruct_0.4.Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb23bf489731f6f376b8ca309b07d2bb74f9a2097cb6abe9329ab567bb597648
3
+ size 5290072576
vikhr-7b-instruct_0.4.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d187019293acbe818f9ca75d508d6bf7d4331ed77ab26b08f28dbe56778f4093
3
+ size 6260043616
vikhr-7b-instruct_0.4.Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14054eb51b3132198f599bf1bc19443d31bb3044cd6bd6bd4511c2e451619402
3
+ size 8107280544
vikhr-7b-instruct_0.4.fp16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85acc21248ecd68e1c3f1a4f5d817c22a8ef26928ba797ebc462f257c0435bc
3
+ size 15257874752
vikhr-7b-instruct_0.4.fp16.gguf.Imatrix.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f2fec96e045da198bdd5296a06852d5d4ffecd29bbcad94204931650f6d2e7
3
+ size 4988179