add files
Browse files- .gitattributes +1 -0
- .gitignore +8 -0
- Makefile +54 -0
- README.md +12 -0
- SHA256SUMS +15 -0
- open-llama-7b-f16.gguf +3 -0
- open-llama-7b-q2_K.gguf +3 -0
- open-llama-7b-q3_K_L.gguf +3 -0
- open-llama-7b-q3_K_M.gguf +3 -0
- open-llama-7b-q3_K_S.gguf +3 -0
- open-llama-7b-q4_0.gguf +3 -0
- open-llama-7b-q4_1.gguf +3 -0
- open-llama-7b-q4_K_M.gguf +3 -0
- open-llama-7b-q4_K_S.gguf +3 -0
- open-llama-7b-q5_0.gguf +3 -0
- open-llama-7b-q5_1.gguf +3 -0
- open-llama-7b-q5_K_M.gguf +3 -0
- open-llama-7b-q5_K_S.gguf +3 -0
- open-llama-7b-q6_K.gguf +3 -0
- open-llama-7b-q8_0.gguf +3 -0
.gitattributes
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gguf filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 10 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
llama.cpp*/
|
| 2 |
+
venv/
|
| 3 |
+
pytorch_model*.bin
|
| 4 |
+
*.sha
|
| 5 |
+
*.tar.gz
|
| 6 |
+
tokenizer.model
|
| 7 |
+
config.json
|
| 8 |
+
tokenizer_config.json
|
Makefile
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MODEL_NAME= open-llama-7b
|
| 2 |
+
PYTHON?= python
|
| 3 |
+
LLAMA_BUILD= 1132
|
| 4 |
+
LLAMA_TAR= b$(LLAMA_BUILD).tar.gz
|
| 5 |
+
LLAMA_DIR= llama.cpp-b$(LLAMA_BUILD)
|
| 6 |
+
LLAMA_FLAGS=
|
| 7 |
+
HF_REPO= openlm-research/open_llama_7b
|
| 8 |
+
HF_REF= main
|
| 9 |
+
HF_FILES= pytorch_model-00001-of-00002.bin \
|
| 10 |
+
pytorch_model-00002-of-00002.bin \
|
| 11 |
+
tokenizer.model \
|
| 12 |
+
config.json \
|
| 13 |
+
tokenizer_config.json
|
| 14 |
+
$(HF_FILES): SITE= https://huggingface.co/$(HF_REPO)/resolve/$(HF_REF)
|
| 15 |
+
$(LLAMA_TAR): SITE= https://github.com/ggerganov/llama.cpp/archive/refs/tags
|
| 16 |
+
|
| 17 |
+
QUANTS= f16 q4_0 q4_1 q5_0 q5_1 q8_0 \
|
| 18 |
+
q2_K \
|
| 19 |
+
q3_K_S q3_K_M q3_K_L \
|
| 20 |
+
q4_K_S q4_K_M \
|
| 21 |
+
q5_K_S q5_K_M \
|
| 22 |
+
q6_K
|
| 23 |
+
|
| 24 |
+
FILES= $(HF_FILES) $(LLAMA_TAR)
|
| 25 |
+
MODEL_FILES= $(foreach q,$(QUANTS),$(MODEL_NAME)-$(q).gguf)
|
| 26 |
+
|
| 27 |
+
.PHONY: all
|
| 28 |
+
all: $(MODEL_FILES) SHA256SUMS
|
| 29 |
+
|
| 30 |
+
$(FILES):
|
| 31 |
+
curl -L -o $@ --url $(SITE)/$@
|
| 32 |
+
|
| 33 |
+
$(LLAMA_DIR): | $(LLAMA_TAR)
|
| 34 |
+
tar -xf $(LLAMA_TAR)
|
| 35 |
+
|
| 36 |
+
$(LLAMA_DIR)/quantize: | $(LLAMA_DIR)
|
| 37 |
+
$(MAKE) -C $(LLAMA_DIR) $(LLAMA_FLAGS) quantize
|
| 38 |
+
|
| 39 |
+
venv:
|
| 40 |
+
$(PYTHON) -m venv venv
|
| 41 |
+
venv/bin/pip install -e $(LLAMA_DIR)/gguf-py
|
| 42 |
+
venv/bin/pip install -r $(LLAMA_DIR)/requirements.txt
|
| 43 |
+
|
| 44 |
+
$(MODEL_NAME)-f16.gguf: $(HF_FILES) | $(LLAMA_DIR) venv
|
| 45 |
+
venv/bin/python $(LLAMA_DIR)/convert.py --outtype f16 --outfile $@ .
|
| 46 |
+
|
| 47 |
+
$(MODEL_NAME)-q%.gguf: $(MODEL_NAME)-f16.gguf | $(LLAMA_DIR)/quantize
|
| 48 |
+
$(LLAMA_DIR)/quantize $< $@ q$*
|
| 49 |
+
|
| 50 |
+
%.sha: %
|
| 51 |
+
sha256sum $< > $@
|
| 52 |
+
|
| 53 |
+
SHA256SUMS: $(addsuffix .sha,$(MODEL_FILES))
|
| 54 |
+
cat $^ > $@
|
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
# gguf versions of OpenLLaMa 7B
|
| 6 |
+
|
| 7 |
+
- Version: 1T tokens final version
|
| 8 |
+
- Project: [OpenLLaMA: An Open Reproduction of LLaMA](https://github.com/openlm-research/open_llama)
|
| 9 |
+
- Model: [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)
|
| 10 |
+
- [llama.cpp](https://github.com/ggerganov/llama.cpp): build 1012 (6381d4e) or later
|
| 11 |
+
- [ggml version](https://huggingface.co/SlyEcho/open_llama_7b_ggml)
|
| 12 |
+
|
| 13 |
+
## Perplexity on wiki.test.406
|
| 14 |
+
|
| 15 |
+
Coming soon...
|
SHA256SUMS
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
6c4f992e504b04bcb3fbb86fcf9e3ee6729d3f68c5c9022dd67a2e5e7fea0aca open-llama-7b-f16.gguf
|
| 2 |
+
788b1a3e1d4568f77c4ba1310ddcfb095e77fc402a234224f51c97898b234209 open-llama-7b-q4_0.gguf
|
| 3 |
+
faa5325919badd6f9224297a99fd43d3e834d646b9790988998b46701d46c716 open-llama-7b-q4_1.gguf
|
| 4 |
+
1998c929dbfbaea8fa213e9cb539cd2fab77e08d29ae0939316e2f389167cedc open-llama-7b-q5_0.gguf
|
| 5 |
+
7774c1d5f135084b94d100d969ea04d6c925746e1ab9f5c0d136196067e3dcf8 open-llama-7b-q5_1.gguf
|
| 6 |
+
a5bd3d01e67e2f570266c300a6cf223f5e8dee82d3efe8719c50e94b41b60ef3 open-llama-7b-q8_0.gguf
|
| 7 |
+
ea8f67d92a85d31e1a0fbac4d7afdb4bbe5f2943b9ad51da639be982f4ddcde7 open-llama-7b-q2_K.gguf
|
| 8 |
+
49d71159eeb2db65ab1fb66d3170fd095f952f4d532aa9af8cd6fb161b249fbd open-llama-7b-q3_K_S.gguf
|
| 9 |
+
64c1fee5e632d4bdfc70ca3511bb94bbf34a96f494100533210146b5211dcfee open-llama-7b-q3_K_M.gguf
|
| 10 |
+
71bd8c1c1c59580f39f5f02fc666fffef9fd37aab039daae0dcaf6a7f0168e9e open-llama-7b-q3_K_L.gguf
|
| 11 |
+
f6be12296fe5e6ddb1a74f21b149a996f3025aad2bc5ea7639581e2f5bac1bcd open-llama-7b-q4_K_S.gguf
|
| 12 |
+
840cdcd6f94dc5a39aa863dc7c213a35eafebcbcb582b50836cfdf1ca4ac7ac0 open-llama-7b-q4_K_M.gguf
|
| 13 |
+
01ced54406fb3147a01d720812e9881a4ede81bc603185a91dc9d3145bd74129 open-llama-7b-q5_K_S.gguf
|
| 14 |
+
ad4fabb67cae58c5ba6233c3403e46096a9e3856d9b5360a3fa54463609c2374 open-llama-7b-q5_K_M.gguf
|
| 15 |
+
cceafae725974a9c295f4985af934c2ed39de40ae919d34de545995a6aea9639 open-llama-7b-q6_K.gguf
|
open-llama-7b-f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c4f992e504b04bcb3fbb86fcf9e3ee6729d3f68c5c9022dd67a2e5e7fea0aca
|
| 3 |
+
size 13478139232
|
open-llama-7b-q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea8f67d92a85d31e1a0fbac4d7afdb4bbe5f2943b9ad51da639be982f4ddcde7
|
| 3 |
+
size 2825975168
|
open-llama-7b-q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bd8c1c1c59580f39f5f02fc666fffef9fd37aab039daae0dcaf6a7f0168e9e
|
| 3 |
+
size 3597145472
|
open-llama-7b-q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64c1fee5e632d4bdfc70ca3511bb94bbf34a96f494100533210146b5211dcfee
|
| 3 |
+
size 3298039168
|
open-llama-7b-q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d71159eeb2db65ab1fb66d3170fd095f952f4d532aa9af8cd6fb161b249fbd
|
| 3 |
+
size 2948339072
|
open-llama-7b-q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:788b1a3e1d4568f77c4ba1310ddcfb095e77fc402a234224f51c97898b234209
|
| 3 |
+
size 3825841536
|
open-llama-7b-q4_1.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faa5325919badd6f9224297a99fd43d3e834d646b9790988998b46701d46c716
|
| 3 |
+
size 4238783872
|
open-llama-7b-q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:840cdcd6f94dc5a39aa863dc7c213a35eafebcbcb582b50836cfdf1ca4ac7ac0
|
| 3 |
+
size 4081038720
|
open-llama-7b-q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6be12296fe5e6ddb1a74f21b149a996f3025aad2bc5ea7639581e2f5bac1bcd
|
| 3 |
+
size 3856774528
|
open-llama-7b-q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1998c929dbfbaea8fa213e9cb539cd2fab77e08d29ae0939316e2f389167cedc
|
| 3 |
+
size 4651726208
|
open-llama-7b-q5_1.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7774c1d5f135084b94d100d969ea04d6c925746e1ab9f5c0d136196067e3dcf8
|
| 3 |
+
size 5064668544
|
open-llama-7b-q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4fabb67cae58c5ba6233c3403e46096a9e3856d9b5360a3fa54463609c2374
|
| 3 |
+
size 4783191424
|
open-llama-7b-q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ced54406fb3147a01d720812e9881a4ede81bc603185a91dc9d3145bd74129
|
| 3 |
+
size 4651726208
|
open-llama-7b-q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cceafae725974a9c295f4985af934c2ed39de40ae919d34de545995a6aea9639
|
| 3 |
+
size 5529228672
|
open-llama-7b-q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5bd3d01e67e2f570266c300a6cf223f5e8dee82d3efe8719c50e94b41b60ef3
|
| 3 |
+
size 7161124224
|