Hugging Face's logo

sh2orc
/
Llama-3-Korean-12B

Text Generation
Transformers
Safetensors
llama
Merge
mergekit
lazymergekit
sh2orc
bccard
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sh2orc commited on
Commit
4778fd7
β€’
1 Parent(s): 6721b58

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. README.md +3 -15
  2. config.json +1 -1
  3. model-00001-of-00005.safetensors +1 -1
  4. model-00002-of-00005.safetensors +1 -1
  5. model-00003-of-00005.safetensors +1 -1
  6. model-00004-of-00005.safetensors +1 -1
  7. model-00005-of-00005.safetensors +1 -1
README.md CHANGED
@@ -8,13 +8,13 @@ tags:
8
  - bllososm
9
 
10
  base_model:
11
- - sh2orc/Llama-3-Korean-8B
12
  ---
13
 
14
  # Llama-3-Korean-12B
15
 
16
  Llama-3-Korean-12B is a merge of the following models using LazyMergekit:
17
- * [sh2orc/Llama-3-Korean-8B](https://huggingface.co/sh2orc/Llama-3-Korean-8B)
18
 
19
  - Dataset:
20
  - [maywell/ko_wikidata_QA](https://huggingface.co/datasets/maywell/ko_wikidata_QA)
@@ -43,16 +43,4 @@ pipeline = transformers.pipeline(
43
 
44
  outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
45
  print(outputs[0]["generated_text"])
46
- ```
47
-
48
-
49
- ## πŸ’Ό Q&A
50
-
51
- __Q. λ‚˜ν˜œμ„μ— λŒ€ν•΄μ„œ μ•Œλ €μ€˜__ <br>
52
- A. λ‚˜ν˜œμ„μ€ 1900λ…„ 4μ›” 6일에 νƒœμ–΄λ‚œ ν•œκ΅­μ˜ ν™”κ°€μ΄μž μž‘κ°€λ‘œ, 1934λ…„ 10μ›” 9일에 세상을 λ– λ‚¬μŠ΅λ‹ˆλ‹€. κ·Έλ…€λŠ” 1918λ…„λΆ€ν„° 1923λ…„κΉŒμ§€ λ―Έμˆ ν•™κ΅λ₯Ό λ‹€λ…”μœΌλ©°, 1923λ…„λΆ€ν„° 1934λ…„κΉŒμ§€ ν™”κ°€λ‘œ ν™œλ™ν–ˆμŠ΅λ‹ˆλ‹€. κ·Έλ…€μ˜ μž‘ν’ˆμ€ 주둜 μ—¬μ„±μ˜ μ‚Άκ³Ό μ—¬μ„±μ˜ κΆŒλ¦¬μ— λŒ€ν•œ 주제λ₯Ό 닀루며, κ·Έλ…€μ˜ μž‘ν’ˆμ€ ν•œκ΅­ ν˜„λŒ€λ―Έμˆ μ˜ λ°œμ „μ— 큰 영ν–₯을 λ―Έμ³€μŠ΅λ‹ˆλ‹€.
53
-
54
- __Q. κ±΄κ°•ν•˜κ²Œ μ‚΄λ €λ©΄?__ <br>
55
- A. κ±΄κ°•ν•˜κ²Œ μ‚΄λ €λ©΄, λ¨Όμ € κ±΄κ°•ν•œ 식단을 μœ μ§€ν•˜κ³ , μΆ©λΆ„ν•œ μš΄λ™μ„ ν•˜λ©°, μΆ©λΆ„ν•œ 수면과 νœ΄μ‹ μ‹œκ°„μ„ κ°–λŠ” 것이 μ€‘μš”ν•©λ‹ˆλ‹€. λ˜ν•œ 슀트레슀λ₯Ό κ΄€λ¦¬ν•˜κ³ , κ±΄κ°•ν•œ μƒν™œμŠ΅κ΄€μ„ μœ μ§€ν•˜λŠ” 것이 μ€‘μš”ν•©λ‹ˆλ‹€. λ˜ν•œ, κ±΄κ°•ν•œ 식단을 μœ μ§€ν•˜κ³ , κ±΄κ°•ν•œ μƒν™œμŠ΅κ΄€μ„ μœ μ§€ν•˜λŠ” 것이 μ€‘μš”ν•©λ‹ˆλ‹€.
56
-
57
- __Q. 2μ°¨μ„Έκ³„λŒ€μ „μ— λŒ€ν•΄μ„œ μ•Œλ €μ€˜__ <br>
58
- A. 2μ°¨μ„Έκ³„λŒ€μ „μ€ 1939λ…„λΆ€ν„° 1945λ…„κΉŒμ§€ μ§„ν–‰λœ 세계 λŒ€μ „μœΌλ‘œ, 독일과 μ†Œλ ¨μ΄ μ „μŸμ— μ°Έμ—¬ν–ˆμŠ΅λ‹ˆλ‹€. 이 μ „μŸμ€ 1939λ…„ 9μ›” 1일 독일이 ν΄λž€λ“œμ— μΉ¨κ³΅ν•˜λ©΄μ„œ μ‹œμž‘λ˜μ—ˆκ³ , 1945λ…„ 5μ›” 8일 독일이 연합ꡰ에 ν•­λ³΅ν•˜λ©΄μ„œ μ’…λ£Œλ˜μ—ˆμŠ΅λ‹ˆλ‹€. 이 μ „μŸμ€ 1939λ…„λΆ€ν„° 1945λ…„κΉŒμ§€ 6λ…„ λ™μ•ˆ μ§„ν–‰λ˜μ—ˆμœΌλ©°, 2μ°¨μ„Έκ³„λŒ€μ „μ€ 2μ°¨λŒ€μ „μœΌλ‘œ μ•Œλ €μ Έ μžˆμŠ΅λ‹ˆλ‹€.
 
8
  - bllososm
9
 
10
  base_model:
11
+ - MLP-KTLim/llama-3-Korean-Bllossom-8B
12
  ---
13
 
14
  # Llama-3-Korean-12B
15
 
16
  Llama-3-Korean-12B is a merge of the following models using LazyMergekit:
17
+ * [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
18
 
19
  - Dataset:
20
  - [maywell/ko_wikidata_QA](https://huggingface.co/datasets/maywell/ko_wikidata_QA)
 
43
 
44
  outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
45
  print(outputs[0]["generated_text"])
46
+ ```
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "sh2orc/Llama-3-Korean-12B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "./Llama-3-Korean-12B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
model-00001-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b3b08b46ec84112a9d9a0dbbfa4e484bf1fe11642285238bd3eed962497d1a8
3
  size 4997129176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57aac7ec7f876f06d4e4783bca9455f9bebeb577812cb64373e8819c5a303e08
3
  size 4997129176
model-00002-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3704daa8fa433bd682a0f517b30d139e593dbef1911c4b315ef1d9f4ab0eb918
3
  size 4999819328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab8d314f6e161354f01d58990eb8541d458f2d194105a2945c4125fa820f7f6
3
  size 4999819328
model-00003-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ddd43092efab744cc86579b76b939a20ca9b4095dba9b99d3d224f565ef588f
3
  size 4915916184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13d8bff6d7a18d15d97a3b41dddd8394068b5295e9b427fe8f372c747637564
3
  size 4915916184
model-00004-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0fdd6b9822ee480d37b527c37ec73fdfe6784228fbde9abe65650034f60380d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92f70ba333f4aeb72bde03460e513e1de17d31b53a04221e3ed4b19e9f1271b
3
  size 4915916176
model-00005-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23ebc35160c1bdc678abbfeb346bf707aed8c6091a2844c0b5c2d09ba8577b98
3
  size 3487151808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e269a6fb394c8771202e45e55fcfd75de5ae0e61873e6483d44e82a74f43bf0e
3
  size 3487151808