HappyZ happyz
happyz synced commits to refs/pull/7388/head at happyz/llama.cpp from mirror 2024-05-20 23:06:36 -07:00
cc98fddcb1 tests : set explicit temperature
8ed8fa9733 tests : fix the fix 0.8f -> 0.8
189963283c server : increase timeout
f159c9d2b1 server : don't pass temperature as string
2789baf480 tests : fix --keep_split -> --keep-split (#7374)
Compare 8 commits »
happyz synced commits to refs/pull/7379/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:36 -07:00
fb32f50834 feat: Add hf model mapping descriptors for each repo
a3bdac091c chore: Remove unused enum import reference
6296206392 chore: Apply deduped token type references
a35b76755f Merge branch 'master' into auto-model-support
Compare 41 commits »
happyz synced commits to refs/pull/7392/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:36 -07:00
fe425436b1 Merge ae3b805a487df7b401d765e2509b918784a37aa0 into 917dc8cfa6
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7383/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:36 -07:00
0ce17756f4 Merge 5ef84eadd69f9dc4eb9c9e8396b05953e3694e49 into 917dc8cfa6
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7379/head at happyz/llama.cpp from mirror 2024-05-20 23:06:36 -07:00
fb32f50834 feat: Add hf model mapping descriptors for each repo
a3bdac091c chore: Remove unused enum import reference
6296206392 chore: Apply deduped token type references
a35b76755f Merge branch 'master' into auto-model-support
aed0573f68 proto: Add experimental vocab pre-tokenizer regular expressions
Compare 34 commits »
happyz synced commits to refs/pull/7375/head at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
7fb66eb58c server : fix test regexes
happyz synced commits to refs/pull/7353/head at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
2e70b6e374 examples: cache hf model when --model not provided
5372f9bdb0 examples: cache hf model when --model not provided
Compare 2 commits »
happyz synced commits to refs/pull/7373/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7353/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
2e70b6e374 examples: cache hf model when --model not provided
Compare 15 commits »
happyz synced commits to refs/pull/7359/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7350/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:35 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
af621975bb SimpleChat:JS:CI: Avoid space at end of jsdoc param line
Compare 18 commits »
happyz synced commits to refs/pull/7329/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 15 commits »
happyz synced commits to refs/pull/7350/head at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
af621975bb SimpleChat:JS:CI: Avoid space at end of jsdoc param line
3fc607f832 SimpleChat: Screen fixed view and scrolling, Printing full
e5000cdb83 SimpleChat: Rename simplechat.html to index.html, update readme
6597fafeae SimpleChat: Make vertical layout better responsive (flex based)
dfadac7813 SimpleChat: textarea for multiline user chat, inturn shift+enter 4 enter
Compare 5 commits »
happyz synced commits to refs/pull/7342/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 14 commits »
happyz synced commits to refs/pull/7328/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
f3011f5088 Merge 69f815d4bb07872283e518d1356b0751644e96e2 into 213e90ed73
213e90ed73 ggml-opencl, llama: using reserve() if count already known (#7272)
65c58207ec ggml : add loongarch lsx and lasx support (#6454)
1cc0155d04 server : tuning tests (#7388)
e932094d58 server : return error on too large embedding input (#7389)
Compare 6 commits »
happyz synced commits to refs/pull/7326/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7321/head at happyz/llama.cpp from mirror 2024-05-20 23:06:34 -07:00
7f5255a709 Remove messages
03344c1e78 Formatting
e79bfca781 Update SYCL upscale operation
213e90ed73 ggml-opencl, llama: using reserve() if count already known (#7272)
65c58207ec ggml : add loongarch lsx and lasx support (#6454)
Compare 58 commits »
happyz synced commits to refs/pull/7315/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:33 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7300/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:33 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »
happyz synced commits to refs/pull/7269/merge at happyz/llama.cpp from mirror 2024-05-20 23:06:32 -07:00
917dc8cfa6 Tokenizer SPM fixes for phi-3 and llama-spm (#7375)
fabf30b4c4 llama : remove Persimmon (#7408)
20385cebcc perplexity: update README FP16 results [no ci] (#7413)
db10f01310 rpc : track allocated buffers (#7411)
Compare 13 commits »